© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81190
    Prev
    Next
    INDEX
    Explanations

    @param and @returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ki
    0.54
     ki
    0.52
     Ens
    0.50
    )}}{
    0.46
    Gest
    0.46
     KI
    0.46
     Akin
    0.46
     hirs
    0.45
    )}(
    0.44
     CCI
    0.44
    POSITIVE LOGITS
     прав
    0.43
    إن
    0.43
    वानी
    0.42
    ющей
    0.40
     सीरीज
    0.40
    Denominator
    0.40
     huyền
    0.39
    Progress
    0.39
     AngularJS
    0.39
     دنی
    0.38
    Activations Density 0.001%

    No Known Activations