© 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. 43832
    Prev
    Next
    INDEX
    Explanations

    log following quote

    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
    菰
    0.44
    ೇನೆ
    0.43
     queim
    0.43
    ક્રિય
    0.43
    釁
    0.43
    alé
    0.42
    ťou
    0.42
     sri
    0.42
     sinon
    0.42
     positivas
    0.41
    POSITIVE LOGITS
    世纪
    0.48
    。）
    0.48
     भव्य
    0.46
    !)
    0.45
    École
    0.45
     Afternoon
    0.44
     انقلاب
    0.44
    ৷
    0.43
     Architectural
    0.42
     INTRODUCTION
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.