© 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. 184851
    Prev
    Next
    INDEX
    Explanations

    voice, market, and exposure related terms

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

    breaking down tasks

    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
     платформа
    0.48
     LEVELS
    0.47
     вдоль
    0.47
     혹은
    0.46
    絞
    0.46
    ૨
    0.45
     చెందిన
    0.45
    atsi
    0.45
     ಮೂಲಕ
    0.45
     помимо
    0.45
    POSITIVE LOGITS
     জানিতে
    0.44
     admitting
    0.41
     negoci
    0.41
    लिनी
    0.41
    저
    0.40
     favorable
    0.39
     compensated
    0.39
     resultant
    0.39
     obtainable
    0.39
     GTEST
    0.39
    Activations Density 0.000%

    No Known Activations