© 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. 142791
    Prev
    Next
    INDEX
    Explanations

    wall climb, my husband, www

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

    prevent sprinkler water

    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
    ющихся
    0.54
    ну
    0.47
     corresponding
    0.45
     asterisk
    0.45
     unregistered
    0.45
     landing
    0.44
    ющегося
    0.44
    ‪
    0.43
    ڃ
    0.43
     uploading
    0.42
    POSITIVE LOGITS
    ION
    0.56
     IONS
    0.56
    RAS
    0.50
    EMPL
    0.49
    Oe
    0.48
    tive
    0.48
    DIRECT
    0.47
    firm
    0.47
    tions
    0.47
    FRA
    0.46
    Activations Density 0.000%

    No Known Activations