© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 20376
    Prev
    Next
    INDEX
    Explanations

    people or groups being described

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

    'P' notation

    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
    ソー
    0.50
    COMP
    0.47
    主な
    0.47
    <h3>
    0.45
    mixing
    0.45
    tg
    0.45
    module
    0.44
    import
    0.44
    setHora
    0.43
    本
    0.43
    POSITIVE LOGITS
    ানক
    0.52
    ailles
    0.45
    ров
    0.45
     ছুঁ
    0.43
    ళ్లు
    0.41
     repeat
    0.41
     outdoors
    0.41
     inds
    0.41
    รง
    0.41
     என்க
    0.41
    Activations Density 0.001%

    No Known Activations