© 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. 64580
    Prev
    Next
    INDEX
    Explanations

    operations, commands, input/output

    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
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -1.02
    ührt
    -0.94
    Trang
    -0.91
    渭
    -0.90
    trung
    -0.85
     Ř
    -0.84
    ган
    -0.83
    Impro
    -0.83
     egz
    -0.83
     in
    -0.82
    POSITIVE LOGITS
     Befehl
    0.97
    是想
    0.93
    atórios
    0.93
    ごちそう
    0.92
    命令
    0.89
     adesso
    0.89
    ねぎ
    0.89
     VIP
    0.89
     input
    0.88
    lossians
    0.88
    Activations Density 0.004%

    No Known Activations