© 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. 127963
    Prev
    Next
    INDEX
    Explanations

    btc price

    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
     históricos
    -0.95
     urbanos
    -0.94
     actuales
    -0.90
    ופה
    -0.89
    ęki
    -0.88
    有两个
    -0.87
     current
    -0.85
    ൊ
    -0.85
    mbing
    -0.83
    abito
    -0.83
    POSITIVE LOGITS
     gré
    0.86
     vitamina
    0.83
     etui
    0.81
    лкой
    0.79
    Additional
    0.79
     magasiner
    0.79
     oignon
    0.79
     التهاب
    0.77
    sarung
    0.77
    cade
    0.76
    Activations Density 0.013%

    No Known Activations