© 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. 102229
    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
     árbitro
    -1.01
     abnormalities
    -1.00
    ☺☺
    -0.94
    ولت
    -0.89
    ometers
    -0.88
     Certificado
    -0.88
     presencial
    -0.87
     éditions
    -0.86
    ͢
    -0.84
     '
    -0.84
    POSITIVE LOGITS
     qualquer
    0.95
    Conven
    0.94
    ⑫
    0.93
    チール
    0.92
    ﹋
    0.90
    書房
    0.87
    ərb
    0.84
    endenza
    0.84
    特に
    0.82
     wojny
    0.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.