© 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 · 22-GEMMASCOPE-RES-131K · 33564 ｜ Neuronpedia

Home
Gemma-2-27B
22-GEMMASCOPE-RES-131K
33564

INDEX

Explanations

programming annotations

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_22/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(

-1.34

主播

-1.27

-1.27

-1.25

 estante

-1.24

 dilaksanakan

-1.24

 armado

-1.23

 helicóptero

-1.23

 estufa

-1.23

 Autorisations

-1.23

POSITIVE LOGITS

↵

2.14

“

1.52

1.49

↵↵

1.45

1.44

1.44

1.41

1.41

1.38

1.38

Activations Density 0.001%

No Known Activations