© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2928
    Prev
    Next
    INDEX
    Explanations

    individual factors and battles

    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_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    er
    5.06
    ة
    4.85
    л
    4.74
    ার
    4.55
    र
    3.83
    ר
    3.77
    ed
    3.67
    ा
    3.66
    ل
    3.66
    ي
    3.55
    POSITIVE LOGITS
    𝖊
    3.69
    𝖔
    3.59
    вости
    3.28
    sorption
    3.22
     oblige
    3.21
     šta
    3.21
    𝖚
    3.19
    ηση
    3.17
    های
    3.12
    ners
    3.10
    Activations Density 0.372%

    No Known Activations