© 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-3-27B · 31-GEMMASCOPE-2-RES-262K · 83673 ｜ Neuronpedia

Home
Gemma-3-27B
31-GEMMASCOPE-2-RES-262K
83673

INDEX

Explanations

foreign language words

np_acts-logits-general · gemini-2.5-flash-lite

past relevance

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 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

aad

0.49

0.48

aat

0.46

格

0.46

ur

0.45

BLO

0.45

aac

0.45

BJ

0.44

AMAN

0.44

aldo

0.43

POSITIVE LOGITS

 provavelmente

0.50

 deniz

0.49

 ۲۰۱

0.49

 выну

0.47

 เมื่อ

0.46

 થય

0.46

 regrets

0.45

ໜ

0.45

⑪

0.45

 hängt

0.44

Activations Density 0.001%

No Known Activations