© 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 · 22-GEMMASCOPE-RES-131K · 16552 ｜ Neuronpedia

Home
Gemma-2-27B
22-GEMMASCOPE-RES-131K
16552

INDEX

Explanations

(now Oslo)

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

Negative Logits

TestBed

-1.08

new

-1.04

medlem

-0.99

 nuevos

-0.99

 nowej

-0.97

-0.95

 рецепта

-0.95

 urethra

-0.94

ologie

-0.93

ૉ

-0.93

POSITIVE LOGITS

 later

1.32

 همچنین

1.06

later

1.05

 pozdě

1.04

 with

0.99

 LATER

0.96

 списка

0.94

Later

0.94

脚步

0.94

̴

0.92

Activations Density 0.103%

No Known Activations