© 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. 75346
    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
    ֻ
    -1.05
    kript
    -1.03
     arabe
    -0.96
    antly
    -0.96
    🇧
    -0.96
    髫
    -0.96
    泔
    -0.94
     Septiembre
    -0.94
     menar
    -0.93
    ¡¡¡
    -0.93
    POSITIVE LOGITS
    Crema
    1.13
    levis
    1.09
     leyendo
    1.05
     escribiendo
    1.05
     тогда
    1.04
    madı
    1.03
     付け
    1.00
     mirando
    0.98
     disfrutando
    0.95
     pidiendo
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.