© 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. 48252
    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
    罢
    -0.89
    нологи
    -0.85
    ρα
    -0.85
    ⡿
    -0.85
     exploits
    -0.85
     recopila
    -0.83
     Antes
    -0.82
     loopholes
    -0.82
    がよく
    -0.82
    функ
    -0.81
    POSITIVE LOGITS
     tiver
    1.01
    کنون
    0.97
     разделе
    0.95
    active
    0.94
    fani
    0.92
    cie
    0.91
     ตา
    0.90
     esetben
    0.88
    ttää
    0.88
     even
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.