© 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. 163059
    Prev
    Next
    INDEX
    Explanations

    poll choices appear

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

    questions asking

    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
    lą
    0.54
    ുപത്രി
    0.49
    プリント
    0.48
    btnPrint
    0.47
    ukiyoe
    0.47
    LaunchAction
    0.47
    ricts
    0.47
    鲞
    0.47
    ię
    0.46
    luor
    0.46
    POSITIVE LOGITS
     valida
    0.52
     /
    0.51
     M
    0.50
    >
    0.50
    ,
    0.49
    ~\
    0.49
     LIMITED
    0.47
     asking
    0.46
     extraordin
    0.45
    0
    0.45
    Activations Density 0.001%

    No Known Activations