© 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. 102407
    Prev
    Next
    INDEX
    Explanations

    maintainoccurbrightly

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

    depth and thoroughness

    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
    䙲
    0.48
     пришлось
    0.48
     στιγμή
    0.48
     रुप
    0.48
     придется
    0.48
     юбилей
    0.48
     terecht
    0.46
     ευ
    0.46
     дать
    0.45
     verpflicht
    0.45
    POSITIVE LOGITS
    a
    0.55
    un
    0.55
    loc
    0.48
    골
    0.48
    theme
    0.48
    ポ
    0.48
    lok
    0.47
    임
    0.45
    ل
    0.45
    lie
    0.44
    Activations Density 0.001%

    No Known Activations