© 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. 65089
    Prev
    Next
    INDEX
    Explanations

    color and swatch selection

    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
    green
    -0.90
    GREEN
    -0.87
    yellow
    -0.85
     yellow
    -0.85
     roten
    -0.83
    綠
    -0.83
    lohy
    -0.81
     Quý
    -0.80
    BLUE
    -0.78
     shayari
    -0.77
    POSITIVE LOGITS
     color
    2.66
     colour
    2.23
     Color
    2.23
    color
    2.03
     swatches
    1.93
     swatch
    1.88
    Color
    1.84
     colors
    1.84
     Colour
    1.84
     palette
    1.82
    Activations Density 0.061%

    No Known Activations