© 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-3-4B-IT · 17-GEMMASCOPE-2-RES-16K · 2600 ｜ Neuronpedia

Home
Gemma-3-4B-IT
17-GEMMASCOPE-2-RES-16K
2600

INDEX

Explanations

e-commerce, pricing, LLMs

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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

 intended

1.69

intended

1.68

ﻰ

1.57

Hfn

1.49

 וכ

1.49

फारिश

1.47

ATIONS

1.47

 swear

1.44

ladesh

1.42

ィ

1.39

POSITIVE LOGITS

aik

1.69

inander

1.68

০

1.63

с

1.63

iap

1.61

iul

1.59

iye

1.58

ert

1.57

ché

1.54

ा

1.51

Activations Density 0.127%

No Known Activations