© 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-2-27B · 10-GEMMASCOPE-RES-131K · 112037 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
112037

INDEX

Explanations

wrestling shows and SNL

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_10/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

-1.78

 با

-1.63

-1.59

 alcun

-1.59

-1.55

其他

-1.51

-1.49

-1.49

 alcuna

-1.44

 otros

-1.35

POSITIVE LOGITS

NCBI

1.47

 consideradas

1.46

 toalha

1.42

 ünl

1.41

甞

1.36

 considerados

1.34

rylic

1.31

𓋼

1.30

RAR

1.29

ⅱ

1.29

Activations Density 0.013%

No Known Activations