© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129689
    Prev
    Next
    INDEX
    Explanations

    following address

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

    equidistant points

    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
    Negative Logits
    كيف
    0.49
    將
    0.48
    為
    0.47
    🛖
    0.47
    Pierce
    0.47
     anisotropy
    0.46
    Elems
    0.46
     আপডেট
    0.45
    連續
    0.45
    折扣
    0.45
    POSITIVE LOGITS
    
    0.45
    ки
    0.44
    onbury
    0.43
     मज़
    0.43
     Carrick
    0.42
     Merseyside
    0.42
     माननीय
    0.42
     bölümde
    0.41
     ТВ
    0.41
     Carls
    0.41
    Activations Density 0.000%

    No Known Activations