© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 8105
    Prev
    Next
    INDEX
    Explanations

    lists separated by commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
     veze
    0.90
    仇
    0.89
    ForegroundColor
    0.87
    judgment
    0.81
     salto
    0.81
    เที่
    0.81
    جين
    0.77
    ⿰
    0.77
    coming
    0.75
    เลือด
    0.74
    POSITIVE LOGITS
    among
    2.39
     amongst
    2.34
     among
    2.26
     Amongst
    2.06
     BUT
    1.97
     blant
    1.95
     respectively
    1.94
     say
    1.92
     например
    1.90
     parmi
    1.90
    Activations Density 0.087%

    No Known Activations