© 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. 73934
    Prev
    Next
    INDEX
    Explanations

    concurrency and threading

    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_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
     keten
    -0.99
    movements
    -0.98
    ఉ
    -0.96
     coba
    -0.94
     område
    -0.93
     Использу
    -0.92
     kulit
    -0.91
     entrou
    -0.88
    вість
    -0.88
     Movements
    -0.87
    POSITIVE LOGITS
    仕事
    1.00
    クレジット
    0.97
     then
    0.96
    แล้ว
    0.96
    ทำงาน
    0.90
     trabajo
    0.89
    作業
    0.88
    ٨
    0.88
    なぜ
    0.85
     my
    0.84
    Activations Density 0.077%

    No Known Activations