© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

GEMMA-3-12B · 41-GEMMASCOPE-2-RES-65K · 14000 ｜ Neuronpedia

Home
Gemma-3-12B
41-GEMMASCOPE-2-RES-65K
14000

INDEX

Explanations

much

np_max-act-logits · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Salem

0.56

 yanında

0.55

Ƹ

0.55

 ни

0.54

ாச

0.54

RAJ

0.53

CartVO

0.53

 diocese

0.53

Â

0.52

Â

0.52

POSITIVE LOGITS

 even

0.56

ത്തേ

0.54

 rubrique

0.54

ッキリ

0.49

 ListItem

0.49

 breaker

0.48

 convenient

0.48

 Confidential

0.48

یدم

0.48

lot

0.47

Activations Density 0.017%

No Known Activations