© 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 · 34-GEMMASCOPE-RES-131K · 103667 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
103667

INDEX

Explanations

power play

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

Hamlet

-0.81

 シングル

-0.80

anine

-0.78

amino

-0.74

 tež

-0.73

 closet

-0.73

 chopper

-0.72

 élevés

-0.72

 vsak

-0.71

िन

-0.70

POSITIVE LOGITS

 power

1.74

 Power

1.50

PP

1.32

Power

1.31

power

1.22

 POWER

1.16

 kill

1.10

 killing

1.08

PP

1.07

 killed

1.05

Activations Density 0.011%

No Known Activations