GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
EvilScript
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
EvilScript
Model Tree
google/gemma-4-31B-it
Input Modalities
Output Modalities
Supported Functionality
An activation oracle is trained to accept another model's hidden-state activations (injected via activation steering) and answer questions about them:
This enables interpretability research without access to the target model's logits or generated text -- only its internal representations.
Paper: Confidence and Calibration of Activation Oracles (arXiv:2605.26045)
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelimport torch# Load the base modelbase_model = AutoModelForCausalLM.from_pretrained("google/gemma-4-31B-it",torch_dtype=torch.bfloat16,device_map="auto",)tokenizer = AutoTokenizer.from_pretrained("google/gemma-4-31B-it")# Load the activation oracle LoRAmodel = PeftModel.from_pretrained(base_model, "EvilScript/activation-oracle-gemma-4-31B-it-step-115000")model.eval()
| Parameter | Value |
|---|---|
| Base model | google/gemma-4-31B-it |
| Adapter | LoRA |
| Training tasks | LatentQA, classification, PastLens (next-token), SAE features |
| Activation injection | Steering vectors at intermediate layers |
| Layer coverage | 25%, 50%, 75% depth |
The oracle is trained on a mixture of: