© 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. 44526
    Prev
    Next
    INDEX
    Explanations

    tectonic disaster

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

    API, search, match

    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
     İstifadə
    0.48
     ક્ષ
    0.48
    ļ
    0.47
    wdir
    0.46
    越来越多的
    0.46
    тировать
    0.44
    꺾
    0.44
    일에
    0.44
    日益
    0.44
    ECONOMIC
    0.44
    POSITIVE LOGITS
     be
    0.58
     as
    0.56
     dr
    0.51
     typing
    0.50
     Information
    0.49
     boulder
    0.49
     are
    0.48
     Teenage
    0.48
     astr
    0.47
    tes
    0.46
    Activations Density 0.000%

    No Known Activations