© 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. 6724
    Prev
    Next
    INDEX
    Explanations

    percentage and proportion

    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
    isDirectory
    -0.90
    +="
    -0.83
    rawtypes
    -0.82
     tane
    -0.80
     Nó
    -0.78
     FetchType
    -0.77
    iyor
    -0.77
     pom
    -0.76
     Bà
    -0.75
    []{
    -0.74
    POSITIVE LOGITS
     percentage
    3.70
     proportion
    3.50
     portion
    3.42
     porcentaje
    2.53
    percentage
    2.52
    Percentage
    2.45
     percentages
    2.42
    portion
    2.39
     Percentage
    2.28
    proportion
    2.25
    Activations Density 0.067%

    No Known Activations