© 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. 98782
    Prev
    Next
    INDEX
    Explanations

    color and style

    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
    omás
    -0.87
    どい
    -0.85
    otus
    -0.85
    quinas
    -0.85
     грамм
    -0.84
     Manley
    -0.82
     relief
    -0.81
    íso
    -0.80
    izier
    -0.80
    setup
    -0.79
    POSITIVE LOGITS
     colours
    1.02
     color
    1.00
     colour
    0.96
     Colour
    0.96
     clothes
    0.96
     seasons
    0.95
     colors
    0.94
     season
    0.90
    似
    0.90
     neutrals
    0.88
    Activations Density 0.017%

    No Known Activations