© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 153549
    Prev
    Next
    INDEX
    Explanations

    authorization, authorizations, electronic

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

    list structure punctuation

    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
    ్లా
    0.47
     गांधी
    0.46
     Represents
    0.45
     Arbeiten
    0.45
     Bewert
    0.43
     是
    0.43
    טן
    0.42
    愣
    0.42
    僌
    0.42
     जानते
    0.42
    POSITIVE LOGITS
    /
    0.50
     downloadable
    0.48
     võimalik
    0.46
    腾
    0.45
     authorization
    0.44
    SV
    0.44
     samu
    0.44
     electronic
    0.43
    ile
    0.43
     authorizations
    0.43
    Activations Density 0.000%

    No Known Activations