© 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. 220783
    Prev
    Next
    INDEX
    Explanations

    key companies

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

    Remember when

    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
    प्रदेश
    0.48
    zysz
    0.46
    ہنی
    0.46
    CodeDict
    0.45
    哫
    0.45
    nn
    0.44
    DUNLAND
    0.44
    ीट
    0.43
    orderDisplay
    0.43
    ନା
    0.43
    POSITIVE LOGITS
     zile
    0.49
     the
    0.48
     “
    0.47
     besie
    0.46
     covert
    0.45
     Z
    0.45
     Nokia
    0.45
     Hewlett
    0.44
     গোপনে
    0.44
     THE
    0.44
    Activations Density 0.001%

    No Known Activations