© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GEMMA-2-27B · 22-GEMMASCOPE-RES-131K · 33402 ｜ Neuronpedia

Home
Gemma-2-27B
22-GEMMASCOPE-RES-131K
33402

INDEX

Explanations

articles followed by specific nouns

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-27b-pt-res/layer_22/width_131k

Prompts (Dashboard)

24,576 prompts, 128 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

tr

-1.16

tache

-1.15

hiva

-1.09

-1.09

-1.09

fr

-1.09

ci

-1.08

to

-1.08

 böyle

-1.07

-1.06

POSITIVE LOGITS

Either

1.84

﹝

1.57

 either

1.52

おはよう

1.52

官網

1.50

・・・・・・・・

1.49

either

1.47

＊＊＊＊

1.45

さてさて

1.45

＊＊＊

1.44

Activations Density 0.068%

No Known Activations