© 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 · 34-GEMMASCOPE-RES-131K · 47652 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
47652

INDEX

Explanations

Japan and Japanese references

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_34/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

槇

-1.30

栃木

-1.20

倉

-1.18

鹿児島

-1.15

金沢

-1.14

滝

-1.12

小田

-1.11

愛知

-1.11

宮崎

-1.10

山崎

-1.09

POSITIVE LOGITS

 Japan

2.22

 Japanese

2.17

Japan

1.57

Japanese

1.54

 япон

1.47

ญี่ปุ่น

1.38

 japan

1.31

 Japão

1.29

 اليابان

1.28

 Tokyo

1.25

Activations Density 0.650%

No Known Activations