© 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-2-27B · 10-GEMMASCOPE-RES-131K · 48080 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
48080

INDEX

Explanations

records

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

-1.44

如

-1.41

return

-1.34

 engelsk

-1.34

 anum

-1.30

-1.27

alanta

-1.27

AFTER

-1.23

 baumwolle

-1.21

欖

-1.20

POSITIVE LOGITS

 that

1.95

Typically

1.70

 اكتوبر

1.65

 vínculo

1.61

 Either

1.59

 Профиль

1.57

jį

1.56

 hábito

1.55

桎

1.49

Usually

1.48

Activations Density 0.046%

No Known Activations