© 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. 11899
    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
     poni
    -1.06
     studia
    -1.00
    pende
    -0.95
    ļas
    -0.93
    føl
    -0.93
     kapan
    -0.93
    bookings
    -0.91
     valsty
    -0.91
    HPLC
    -0.90
    Bookings
    -0.90
    POSITIVE LOGITS
     initial
    1.01
     proverbial
    0.98
     Why
    0.91
     Our
    0.90
     They
    0.88
    calcular
    0.85
    引入
    0.84
     Moreover
    0.84
     intentó
    0.84
     Почему
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.