© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 148525
    Prev
    Next
    INDEX
    Explanations

    property, searching, surfing, dangerous, drug

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

    CRISPR, phishing, spot instances, biotech

    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
     các
    0.52
     modem
    0.50
    ృ
    0.46
    стояния
    0.45
    entraî
    0.44
    σό
    0.44
    تباين
    0.44
    시킨
    0.44
     poems
    0.44
    牖
    0.44
    POSITIVE LOGITS
    is
    0.47
    Innovation
    0.46
    Equality
    0.45
     Initiation
    0.45
    wounded
    0.44
     उसमे
    0.43
    It
    0.43
    UN
    0.42
    have
    0.42
    has
    0.42
    Activations Density 0.000%

    No Known Activations