© 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. 117820
    Prev
    Next
    INDEX
    Explanations

    indemnify affiliates and officers

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

    energy and responses

    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
    álov
    0.56
     diagonalizable
    0.51
    푀
    0.51
     physiologically
    0.50
     Rxf
    0.49
    зок
    0.49
     Aarti
    0.48
    analisi
    0.47
    oconvex
    0.47
     kial
    0.46
    POSITIVE LOGITS
     വെള്ള
    0.50
     الدكتور
    0.46
    sensitivity
    0.46
    删除
    0.46
     东
    0.44
     citizenry
    0.44
    CompliancePolicy
    0.43
    ielder
    0.43
    orsement
    0.43
    Sensitivity
    0.43
    Activations Density 0.001%

    No Known Activations