© 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. 29396
    Prev
    Next
    INDEX
    Explanations

    define(

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

    code and latex definitions

    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
     ソ
    0.49
    怿
    0.48
     ვი
    0.47
     일반
    0.47
     erreurs
    0.47
     кі
    0.47
     ส
    0.46
     mochila
    0.46
     rapides
    0.46
     కరో
    0.46
    POSITIVE LOGITS
    an
    0.68
    on
    0.66
    us
    0.58
    in
    0.57
    та
    0.57
    shi
    0.54
    and
    0.52
    st
    0.52
    ون
    0.52
    z
    0.52
    Activations Density 0.000%

    No Known Activations