© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 53834
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     العاده
    -0.81
     വി
    -0.75
     Soon
    -0.75
     ショート
    -0.74
    ñador
    -0.73
     dès
    -0.72
    ativo
    -0.71
     takeout
    -0.71
    Недоліки
    -0.70
    wych
    -0.69
    POSITIVE LOGITS
    ığınız
    0.88
    HasColumnName
    0.85
     builders
    0.80
     pă
    0.80
    Builder
    0.80
     dragons
    0.79
    ẵng
    0.77
     wanda
    0.77
    ături
    0.77
    CardModule
    0.77
    Activations Density 0.001%

    No Known Activations