© 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 · 10-GEMMASCOPE-RES-131K · 59179 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
59179

INDEX

Explanations

consider

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

</b>

-1.90

us

-1.86

Ꮂ

-1.65

to

-1.61

-1.58

-1.55

藹

-1.52

</h1>

-1.45

 everything

-1.45

zieć

-1.43

POSITIVE LOGITS

Отзывы

1.63

不断

1.56

งิน

1.54

 calmness

1.53

 newfound

1.50

maxn

1.48

readFileSync

1.48

 dAtA

1.47

 only

1.47

⇹

1.45

Activations Density 0.032%

No Known Activations