© 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. 2913
    Prev
    Next
    INDEX
    Explanations

    even followed by conjunctions

    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
    я
    1.81
    ي
    1.72
    in
    1.69
    يي
    1.48
    a
    1.48
    i
    1.46
    х
    1.46
    ョン
    1.42
    unki
    1.37
    dataTable
    1.36
    POSITIVE LOGITS
    €™
    1.41
     दहा
    1.37
     vigilance
    1.33
    aires
    1.31
    verband
    1.30
     comprehensive
    1.29
     worrying
    1.29
     accommodation
    1.27
     uphill
    1.25
    եք
    1.23
    Activations Density 0.025%

    No Known Activations