© 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. 115623
    Prev
    Next
    INDEX
    Explanations

    dodge baseball

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

    needs or communicate

    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
     pods
    0.50
     banked
    0.45
    样子
    0.43
    气
    0.42
     lows
    0.42
    ష
    0.42
    某
    0.42
    দি
    0.41
     ATL
    0.41
    정
    0.41
    POSITIVE LOGITS
     circunferencia
    0.56
    切割
    0.52
     احتجاج
    0.49
     пусть
    0.47
     विभाजित
    0.46
     diferenciar
    0.46
     ਉਹ
    0.46
     মুসলমানদের
    0.46
     شنو
    0.45
     ﷺ
    0.45
    Activations Density 0.000%

    No Known Activations