© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92830
    Prev
    Next
    INDEX
    Explanations

    describing colors of things

    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
     white
    -0.90
     whitish
    -0.90
     witte
    -0.89
     silvery
    -0.89
     rotas
    -0.88
    kell
    -0.87
     zwarte
    -0.86
     scarlet
    -0.86
     белом
    -0.86
     bambú
    -0.85
    POSITIVE LOGITS
     plumage
    1.29
     walls
    1.07
     lips
    0.94
     upholstery
    0.89
     leaves
    0.89
    Background
    0.87
     backgrounds
    0.87
     bruise
    0.86
     paints
    0.85
     shirts
    0.85
    Activations Density 0.038%

    No Known Activations