© 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 · 86281 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
86281

INDEX

Explanations

county names and communities

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

禇

-1.55

 kubwa

-1.47

 tenisky

-1.45

 berperan

-1.41

 nyingi

-1.41

 cend

-1.40

やお

-1.40

 palio

-1.39

 kanskje

-1.38

욘

-1.38

POSITIVE LOGITS

すでに

1.54

 river

1.50

</u>

1.49

1.49

1.47

1.39

1.39

de

1.37

?”

1.35

1.34

Activations Density 0.790%

No Known Activations