© 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. 70324
    Prev
    Next
    INDEX
    Explanations

    passive voice

    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_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
    🢒
    -2.09
     reunió
    -1.89
     și
    -1.89
    赑
    -1.87
     và
    -1.83
     of
    -1.81
    嫒
    -1.77
     dê
    -1.71
    ᯾
    -1.68
     և
    -1.66
    POSITIVE LOGITS
    ㈥
    1.89
     hatır
    1.80
    我也
    1.69
     söyl
    1.66
    駈
    1.60
    正如
    1.56
    También
    1.55
     Pediat
    1.55
     This
    1.55
    In
    1.53
    Activations Density 0.011%

    No Known Activations