© 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. 34-GEMMASCOPE-RES-131K
    7. 97926
    Prev
    Next
    INDEX
    Explanations

    right knee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Рі
    -0.75
    愿望
    -0.72
    ร
    -0.71
    読書
    -0.71
    böz
    -0.70
     feiern
    -0.69
    特別な
    -0.68
    อน
    -0.67
     erleben
    -0.66
    ท
    -0.66
    POSITIVE LOGITS
    tské
    0.83
    ADAS
    0.80
    BigInt
    0.80
     عملی
    0.79
     מוע
    0.79
     BigInt
    0.79
     PROB
    0.78
     Ghar
    0.78
     proib
    0.77
    Capability
    0.77
    Activations Density 0.041%

    No Known Activations