© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7197
    Prev
    Next
    INDEX
    Explanations

    Sara followed by surname

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -2.69
    
    -2.67
     และ
    -2.66
     it
    -2.56
     bekannten
    -2.55
    久了
    -2.52
     různých
    -2.50
    ⁛
    -2.48
     която
    -2.41
    ={
    -2.41
    POSITIVE LOGITS
    e
    3.27
    o
    3.02
    x
    2.97
    The
    2.91
    a
    2.77
    ar
    2.56
    を入
    2.48
     DÍA
    2.41
    $
    2.39
    硨
    2.39
    Activations Density 0.003%

    No Known Activations