© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62679
    Prev
    Next
    INDEX
    Explanations

    ui and view in code

    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_34/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
    数据库
    -0.84
    Sommer
    -0.77
    textLabel
    -0.75
    culaire
    -0.74
     Demographic
    -0.73
     inversely
    -0.73
     Fakten
    -0.73
     appartenant
    -0.72
    quelize
    -0.72
     originals
    -0.71
    POSITIVE LOGITS
    utils
    1.08
     componentes
    1.07
    common
    1.06
    Main
    1.03
    tils
    0.94
     common
    0.94
     compone
    0.92
     appétit
    0.92
     ViewModel
    0.92
    components
    0.92
    Activations Density 0.012%

    No Known Activations