© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86779
    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
     MANY
    -0.93
     figlio
    -0.87
     Certainly
    -0.86
    
    -0.85
    vénients
    -0.85
     ayudará
    -0.85
    ﺪ
    -0.84
    Stret
    -0.84
    ва
    -0.83
     расте
    -0.83
    POSITIVE LOGITS
     <=>
    0.98
    ulse
    0.96
     ‘
    0.96
     you
    0.95
     мощность
    0.95
     Lease
    0.94
    culos
    0.93
     Đình
    0.90
     качество
    0.90
     «
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.