© 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. 22-GEMMASCOPE-RES-131K
    7. 10863
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     kvä
    -1.02
    makeat
    -1.02
     terlaris
    -1.00
    pareja
    -0.98
     overseen
    -0.98
     膜
    -0.96
    ♡♡
    -0.95
     kutoka
    -0.94
     aveo
    -0.94
     prostředí
    -0.93
    POSITIVE LOGITS
     if
    1.14
     &
    1.00
     vamos
    0.99
    idopsis
    0.97
     proyec
    0.95
     ellos
    0.93
    真实
    0.93
    bird
    0.93
    する
    0.92
    apen
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.