© 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. 145468
    Prev
    Next
    INDEX
    Explanations

    how many people

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

    color, names, quanitifiers

    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
     quarter
    0.52
     km
    0.51
     cut
    0.51
     back
    0.50
     see
    0.49
    ↵↵
    0.49
     manufacturer
    0.49
     cards
    0.48
     war
    0.47
     style
    0.47
    POSITIVE LOGITS
    fontenc
    0.52
     заболевания
    0.49
    apanam
    0.48
    狍
    0.48
    Formats
    0.48
    犄
    0.48
    சனம்
    0.47
    弐
    0.47
    rophages
    0.47
    υτό
    0.46
    Activations Density 0.001%

    No Known Activations