© 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. 12520
    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
     vannak
    -0.93
    which
    -0.93
     whereby
    -0.91
    =>{
    -0.91
    诲
    -0.84
    serviceWorker
    -0.84
     Głów
    -0.82
     likewise
    -0.82
     материалы
    -0.82
     wherein
    -0.82
    POSITIVE LOGITS
     enlever
    1.03
    ]]
    
    1.02
    ciller
    1.00
    setField
    1.00
    まない
    0.98
    oxia
    0.96
    groep
    0.96
    sonder
    0.94
    隰
    0.92
     criss
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.