© 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. 250860
    Prev
    Next
    INDEX
    Explanations

    follow us on google plus

    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
     contaminate
    0.49
     be
    0.47
     zab
    0.47
     accomplish
    0.47
     simil
    0.46
     hason
    0.46
    レクト
    0.46
    <
    0.46
    ANAL
    0.46
    pubescens
    0.45
    POSITIVE LOGITS
    的故事
    0.53
    Номер
    0.49
    ایش
    0.48
    ())));
    0.48
     Bury
    0.48
     Союза
    0.47
     оригіналу
    0.47
    qr
    0.46
     شماره
    0.46
    ای
    0.46
    Activations Density 0.000%

    No Known Activations