© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40234
    Prev
    Next
    INDEX
    Explanations

    agile development and marketing

    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
    [
    -2.27
    \\
    -2.09
     multitude
    -2.06
    -
    -2.03
     we
    -2.02
     It
    -2.00
    ’
    -1.95
     number
    -1.78
     There
    -1.76
     People
    -1.73
    POSITIVE LOGITS
     土産
    2.17
    蒾
    2.06
    鮠
    2.05
    鲠
    2.00
    勠
    1.98
    ꦫ
    1.96
    assertIs
    1.90
    鯢
    1.88
    𐌼
    1.82
     også
    1.77
    Activations Density 0.005%

    No Known Activations