© 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. 147972
    Prev
    Next
    INDEX
    Explanations

    social and local connections

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

    system administration and file 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
    ಿಕೆ
    0.54
     Ware
    0.50
     způsob
    0.50
    輌
    0.49
     wyk
    0.48
    廠
    0.48
     vypl
    0.47
     بيان
    0.47
     aulas
    0.46
     prostřed
    0.45
    POSITIVE LOGITS
     벗
    0.57
    arı
    0.49
    asam
    0.48
     recovered
    0.47
    नंतर
    0.47
    erebbe
    0.47
    ເລັກ
    0.46
    tiba
    0.45
    yrıca
    0.44
     offseason
    0.43
    Activations Density 0.001%

    No Known Activations