© 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 · 228041 ｜ Neuronpedia

Home
Gemma-3-27B
31-GEMMASCOPE-2-RES-262K
228041

INDEX

Explanations

SE implementation AV PC

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

ቭ

0.55

<unused1>

0.52

 videomuzda

0.49

𒌨

0.49

 ngư

0.48

 Thakur

0.48

VILLE

0.46

鏻

0.46

ଲ

0.46

লস

0.46

POSITIVE LOGITS

خ

0.47

kee

0.46

0.46

 commonly

0.46

نو

0.46

und

0.45

to

0.45

nee

0.45

نت

0.45

ход

0.44

Activations Density 0.000%

No Known Activations