© 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. 74402
    Prev
    Next
    INDEX
    Explanations

    repair and regeneration

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

    travel plan / future

    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
    离子
    0.54
     কর্প
    0.44
    蒙古
    0.44
     Mitigation
    0.44
    鸹
    0.43
    蜇
    0.43
     గ్రామ
    0.43
    推
    0.42
     BitmapFactory
    0.42
     Strategies
    0.42
    POSITIVE LOGITS
    ul
    0.52
    deny
    0.52
    eg
    0.48
    max
    0.48
    is
    0.48
    chio
    0.47
    ț
    0.47
     prosper
    0.47
    le
    0.46
    ie
    0.46
    Activations Density 0.000%

    No Known Activations