© 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. 111458
    Prev
    Next
    INDEX
    Explanations

    quantities, durations, and specific interactions

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

    function, favored, full

    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
     осна
    0.51
    ³.
    0.51
     kü
    0.51
     pression
    0.49
     Carg
    0.48
     åp
    0.47
     Cargo
    0.47
     canlı
    0.46
     tuleb
    0.46
     ü
    0.45
    POSITIVE LOGITS
    ва
    0.49
    てもら
    0.46
    ία
    0.46
    notation
    0.44
     तम
    0.44
     बताने
    0.43
    ала
    0.42
    стики
    0.42
    in
    0.42
    stab
    0.41
    Activations Density 0.000%

    No Known Activations