© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

GEMMA-2-27B · 10-GEMMASCOPE-RES-131K · 22497 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
22497

INDEX

Explanations

color: or image:

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



-2.14

 cambia

-2.00

]$,

-1.95

籥

-1.88

跺

-1.88

 diversa

-1.84

ᚔ

-1.83

 quando

-1.83

蓠

-1.83

)]

-1.82

POSITIVE LOGITS

“

2.06

 colorés

1.92

 normaux

1.91

1.91

ところです

1.84

 originaux

1.80

1.76

 exemplaires

1.74

bundet

1.68

 bouwen

1.65

Activations Density 0.012%

No Known Activations