© 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. 22-GEMMASCOPE-2-RES-16K
    7. 3288
    Prev
    Next
    INDEX
    Explanations

    Chinese terms

    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_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     the
    1.21
     (
    1.09
    -
    0.97
     a
    0.97
     historical
    0.97
     la
    0.94
     regional
    0.94
     -
    0.93
     masquer
    0.93
    .
    0.93
    POSITIVE LOGITS
    能
    1.58
    々
    1.50
    字
    1.37
    心
    1.36
    子
    1.34
    金
    1.33
    作
    1.31
    力
    1.30
    身
    1.29
    子的
    1.29
    Activations Density 0.062%

    No Known Activations