© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-3-12B-IT · 31-GEMMASCOPE-2-RES-16K · 2381 ｜ Neuronpedia

Home
Gemma-3-12B-IT
31-GEMMASCOPE-2-RES-16K
2381

INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 이러한

0.67

 terdapat

0.64

하였

0.58

🌺

0.55

มีการ

0.55

puede

0.54

（

0.54

perhaps

0.54

未能

0.54

（

0.52

POSITIVE LOGITS

 depois

0.78

 BEFORE

0.77

 после

0.75

 AFTER

0.74

 без

0.73

 перед

0.71

 after

0.69

 dopo

0.69

BEFORE

0.68

 before

0.68

Activations Density 0.133%

No Known Activations