© 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. 78116
    Prev
    Next
    INDEX
    Explanations

    time, flexibility, join, counsel, performer, visit

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

    cost and arrangement

    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
    <b>
    0.51
    ISTIC
    0.45
     racional
    0.44
    古代
    0.42
    [
    0.42
    >(
    0.41
     debo
    0.41
     crucially
    0.40
     Христо
    0.39
    </th>
    0.39
    POSITIVE LOGITS
    lensFlare
    0.54
    。『
    0.52
    ﹟
    0.51
    สห
    0.48
    ꩡ
    0.48
    कॉम
    0.47
    serialization
    0.47
    ्लाई
    0.47
    ллі
    0.47
    ্বরের
    0.47
    Activations Density 0.000%

    No Known Activations