© 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. 25535
    Prev
    Next
    INDEX
    Explanations

    numpy scientific code

    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
    readdir
    -0.75
     kapit
    -0.75
    琛
    -0.74
    DLE
    -0.73
     UnityEngine
    -0.73
    loven
    -0.71
     violence
    -0.71
     صفحة
    -0.71
    ्रे
    -0.70
     penser
    -0.70
    POSITIVE LOGITS
     where
    0.82
    GENER
    0.79
    rint
    0.75
    樣的
    0.73
     neón
    0.72
    where
    0.72
    engeti
    0.72
    тератур
    0.71
    issante
    0.70
    oquia
    0.70
    Activations Density 0.021%

    No Known Activations