© 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 · 10937 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
10937

INDEX

Explanations

laundry and washing machines

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

 However

-1.60

ﮩ

-1.48

However

-1.44

had

-1.42

 would

-1.38

 Surprisingly

-1.36

𖥦

-1.34

镦

-1.30

Зміст

-1.30

 could

-1.29

POSITIVE LOGITS

辚

1.56

粜

1.49

 perpé

1.47

 renowned

1.44

何を

1.42

苙

1.41

 замена

1.41

傒

1.40

 เป็น

1.38

獃

1.38

Activations Density 0.015%

No Known Activations