© 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. 10-GEMMASCOPE-RES-131K
    7. 47899
    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
    试试
    -1.02
     welchem
    -1.00
    UEL
    -0.97
     инструментов
    -0.96
    cially
    -0.94
     lombok
    -0.90
     divertida
    -0.90
    べる
    -0.90
    utama
    -0.89
    }\}
    -0.89
    POSITIVE LOGITS
    さっそく
    1.06
     with
    1.05
     pembentukan
    1.03
     lectores
    1.01
     rallado
    0.98
     nebude
    0.95
     kemajuan
    0.95
    não
    0.93
     felhasznál
    0.91
    Ꮉ
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.