© 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. 203760
    Prev
    Next
    INDEX
    Explanations

    available seasons, events, or activities

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

    multilingual text diversity

    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
    יי
    0.57
    a
    0.56
    );
    0.47
    Execution
    0.46
     Ent
    0.45
    á
    0.45
     Architectural
    0.44
     Bay
    0.44
    駭
    0.44
    0.43
    POSITIVE LOGITS
     nguyên
    0.59
     Lạt
    0.55
     gxh
    0.54
     ಏಕೆ
    0.54
     машины
    0.54
     nghệ
    0.52
     lục
    0.52
     uczniów
    0.51
     مشینوں
    0.51
     molécules
    0.51
    Activations Density 0.000%

    No Known Activations