© 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. 75627
    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
    ํ
    -0.90
    انواع
    -0.88
    Ưu
    -0.86
     réjou
    -0.84
     бы
    -0.81
     blé
    -0.80
    Από
    -0.79
     virgin
    -0.79
    kundige
    -0.78
    ಊ
    -0.77
    POSITIVE LOGITS
     motorrad
    0.89
    앗
    0.84
     yako
    0.83
     Scarborough
    0.79
    krish
    0.79
    mitive
    0.78
    succeeded
    0.77
     mentor
    0.73
    goth
    0.73
     Zum
    0.73
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.