© 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. 145491
    Prev
    Next
    INDEX
    Explanations

    quotation marks and delimiters

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

    special characters or code markers

    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
    ك
    0.71
    اا
    0.67
    that
    0.66
    ↵↵
    0.64
    arounds
    0.63
    اك
    0.62
    at
    0.62
    רג
    0.62
    yı
    0.61
    ناب
    0.61
    POSITIVE LOGITS
     Ά
    0.61
     Τ
    0.61
     күз
    0.58
     Ви
    0.55
    è
    0.55
    
    0.55
     फूलों
    0.54
     পড়িয়া
    0.54
     Վ
    0.54
     ново
    0.54
    Activations Density 0.007%

    No Known Activations