© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 187417
    Prev
    Next
    INDEX
    Explanations

    repeated special characters and symbols

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

    code reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ہاتھوں
    0.37
    制品
    0.37
    ٹرول
    0.36
    
    0.36
    워서
    0.36
     numai
    0.35
    觞
    0.34
     Potatoes
    0.34
     आग
    0.34
    монт
    0.34
    POSITIVE LOGITS
    \
    0.46
    dea
    0.44
    t
    0.44
    З
    0.44
    Г
    0.44
    ED
    0.43
    АР
    0.43
    {
    0.43
     Genoa
    0.43
    єї
    0.43
    Activations Density 0.000%

    No Known Activations