© 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. 163578
    Prev
    Next
    INDEX
    Explanations

    proper nouns and abstract concepts

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

    as recognized today

    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
     ('
    0.49
    ${
    0.43
    <sup>
    0.43
    ilir
    0.43
    /
    0.43
    इंट
    0.41
    `${
    0.41
    ;
    0.40
    atonic
    0.40
    ¹.
    0.40
    POSITIVE LOGITS
     بڑھ
    0.52
    ור
    0.46
    تنا
    0.45
     تنا
    0.45
    ಿದ್ದಾನೆ
    0.45
    لح
    0.45
     comer
    0.44
     piazza
    0.44
    isFullscreen
    0.44
     ഭക്ഷ
    0.43
    Activations Density 0.001%

    No Known Activations