© 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. 202986
    Prev
    Next
    INDEX
    Explanations

    accounts, suggests, paying

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

    First, constituent, accounts, file

    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
     مُ
    0.50
     neurotic
    0.48
    unky
    0.48
    uj
    0.48
    '
    0.47
    unos
    0.46
    ale
    0.46
    lation
    0.46
     عج
    0.45
     slew
    0.44
    POSITIVE LOGITS
     Primero
    0.58
    Primero
    0.53
     Yukarı
    0.50
    ходе
    0.48
    ᱢ
    0.48
     tathapi
    0.47
    ренный
    0.47
    ходил
    0.47
    вате
    0.47
    λεκ
    0.47
    Activations Density 0.001%

    No Known Activations