© 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. 208535
    Prev
    Next
    INDEX
    Explanations

    specific work

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

    poetry and project management

    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
     کو
    0.48
    是将
    0.46
    ুঁ
    0.45
    猁
    0.44
    اندا
    0.44
     বিস্তৃত
    0.44
     माप
    0.44
    ریز
    0.43
     गणना
    0.43
    rijke
    0.43
    POSITIVE LOGITS
    o
    0.52
    or
    0.51
     Scribner
    0.50
     Gorman
    0.49
     succumb
    0.48
    oader
    0.46
    zustellen
    0.46
    chy
    0.46
    ७
    0.46
     Ye
    0.45
    Activations Density 0.000%

    No Known Activations