© 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. 82694
    Prev
    Next
    INDEX
    Explanations

    chok, chock, choking

    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
    Course
    -0.68
     lact
    -0.68
     Course
    -0.65
     poveznice
    -0.65
     Tunisie
    -0.63
    satunya
    -0.62
     nguy
    -0.62
    हाँ
    -0.62
     only
    -0.61
     образ
    -0.61
    POSITIVE LOGITS
     ê
    0.73
    шо
    0.72
    splitter
    0.71
     Perkin
    0.69
     hore
    0.68
    CDU
    0.67
     instability
    0.67
    aled
    0.66
     проведения
    0.66
     بنا
    0.66
    Activations Density 0.053%

    No Known Activations