© 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. 99133
    Prev
    Next
    INDEX
    Explanations

    aqua, weather, convection, tiny, clinging, boys

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

    placement and scaling

    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
     工程
    0.54
     为
    0.52
     twenties
    0.51
     জানা
    0.50
     比
    0.49
     特
    0.49
     特別
    0.49
    企业家
    0.49
     文化
    0.48
     公
    0.48
    POSITIVE LOGITS
    д
    0.47
     models
    0.45
    м
    0.44
    й
    0.43
    اوم
    0.43
     perp
    0.43
     pract
    0.42
    اف
    0.42
     mir
    0.42
    कम
    0.42
    Activations Density 0.001%

    No Known Activations