© 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. 157992
    Prev
    Next
    INDEX
    Explanations

    Q, needed

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

    defining variable types

    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
    情報は
    0.56
    螟
    0.45
     문제는
    0.44
    巖
    0.43
    現在は
    0.42
    myCollision
    0.42
    বর্তমানে
    0.42
     supernatant
    0.41
    았던
    0.41
     searchObject
    0.41
    POSITIVE LOGITS
    reserv
    0.50
     gewüns
    0.48
    iones
    0.46
     ù
    0.46
     réserv
    0.46
    charging
    0.46
     sobretudo
    0.45
    ível
    0.45
     konum
    0.45
    jí
    0.44
    Activations Density 0.002%

    No Known Activations