© 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. 48433
    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
    kách
    -1.02
    皇子
    -1.02
    ômes
    -0.98
     странице
    -0.96
    Asts
    -0.94
    lapsingToolbar
    -0.91
     Союза
    -0.91
    Fault
    -0.91
    емые
    -0.91
    基础
    -0.90
    POSITIVE LOGITS
    麻辣
    0.90
    ichteten
    0.84
    MapView
    0.82
    Pall
    0.82
     badkamer
    0.81
    hoeddwyd
    0.81
     построе
    0.81
    屨
    0.81
    Цита
    0.80
     croissance
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.