© 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. 22-GEMMASCOPE-RES-131K
    7. 16529
    Prev
    Next
    INDEX
    Explanations

    measuring, serviced, increased

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     benzer
    -1.20
     目
    -1.02
    ҫ
    -0.97
     auténtico
    -0.95
     sonrası
    -0.93
    zetten
    -0.91
    Kanpo
    -0.90
    ικών
    -0.89
     hoş
    -0.89
    byshev
    -0.88
    POSITIVE LOGITS
     zaragoza
    0.95
     relaciona
    0.94
     consideró
    0.92
     指輪
    0.88
     herbe
    0.88
     raiſ
    0.87
     sledo
    0.84
     katze
    0.84
    咳嗽
    0.83
     cipolla
    0.83
    Activations Density 0.052%

    No Known Activations