© 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. 12584
    Prev
    Next
    INDEX
    Explanations

    quoted first-person speech

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

    Game Guild recreations

    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
     엔
    0.47
     Dunedin
    0.47
     harmful
    0.46
     สอบ
    0.45
     Ravenna
    0.45
     uređ
    0.44
     możliwość
    0.44
     projeto
    0.43
     subsid
    0.43
    ེད་
    0.43
    POSITIVE LOGITS
    та
    0.50
    []){
    0.48
    ль
    0.48
    Achievements
    0.45
    ш
    0.43
    н
    0.43
    ̣c
    0.43
    мни
    0.43
    []);
    0.43
     annuel
    0.43
    Activations Density 0.000%

    No Known Activations