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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129488
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -1.19
     golos
    -0.93
    Ꮀ
    -0.93
    Gai
    -0.88
    ggiare
    -0.88
    戗
    -0.85
     bloquer
    -0.84
    gambarkan
    -0.83
     hùng
    -0.83
    Màu
    -0.83
    POSITIVE LOGITS
    瑆
    1.07
    lamin
    1.00
     sternly
    0.96
     brightened
    0.95
     those
    0.95
     migliori
    0.94
     this
    0.94
     there
    0.94
     penerima
    0.93
                    
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.