© 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 · 129542 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
129542

INDEX

Explanations

same, both, or other

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

-1.24

 elétrica

-1.21

nému

-1.20

brak

-1.20



-1.19

digkeit

-1.17

 sintética

-1.17

 conscientes

-1.16

stwo

-1.15

 thre

-1.15

POSITIVE LOGITS

 will

1.39

 siglo

1.34

 only

1.32

 usai

1.30

 setelah

1.24

 from

1.23

1.21

된

1.20

Only

1.19

 cérami

1.18

Activations Density 0.049%

No Known Activations