© 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. 140002
    Prev
    Next
    INDEX
    Explanations

    long line of women

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

    credit cards or remark examples

    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
    Negative Logits
     logs
    0.49
    日志
    0.49
    oky
    0.48
    "
    0.47
     kuk
    0.45
     claves
    0.44
     neurotic
    0.44
    ok
    0.44
     accro
    0.44
     ziemlich
    0.44
    POSITIVE LOGITS
    ตั้งแต่
    0.52
    чения
    0.52
    遺
    0.51
    <unused50>
    0.50
    ਗਾ
    0.50
    場面積
    0.49
    propto
    0.48
     localisation
    0.48
    ܠܐ
    0.48
    지와
    0.48
    Activations Density 0.001%

    No Known Activations