© 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. 34-GEMMASCOPE-RES-131K
    7. 98981
    Prev
    Next
    INDEX
    Explanations

    full color descriptions

    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
    ="[
    -0.77
     darin
    -0.76
    tan
    -0.73
    theta
    -0.71
    ി
    -0.71
    yang
    -0.69
    configuration
    -0.68
    virtual
    -0.68
     Sack
    -0.67
    yar
    -0.66
    POSITIVE LOGITS
     color
    4.69
     colour
    4.19
    color
    3.78
     Color
    3.72
     COLOR
    3.67
    colour
    3.39
    Color
    3.34
     цвет
    3.33
     Colour
    3.30
     colored
    3.23
    Activations Density 0.082%

    No Known Activations