© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-3-27B-IT · 31-GEMMASCOPE-2-RES-65K · 3380 ｜ Neuronpedia

Home
Gemma-3-27B-IT
31-GEMMASCOPE-2-RES-65K
3380

INDEX

Explanations

binary search code constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

गु

0.38

ᠩ

0.38

बाईल

0.38

𒉈

0.38

 matéria

0.38

៣

0.38

 pertama

0.38

முகம்

0.38

瑆

0.38

produk

0.37

POSITIVE LOGITS

<0xC2>

0.40

0.35

 final

0.35

0.35

</

0.33

 Clean

0.32

hashed

0.32

 backseat

0.32

).

0.31

 destructive

0.31

Activations Density 0.232%

No Known Activations