© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10365
    Prev
    Next
    INDEX
    Explanations

    color palettes and hues

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to vivid visual descriptors—especially color words or rich color-related adjectives.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fakultas
    0.90
     書い
    0.85
    minded
    0.84
     Schriftsteller
    0.84
    ח
    0.81
     международных
    0.79
    lui
    0.79
    ן
    0.79
    university
    0.78
    ERS
    0.77
    POSITIVE LOGITS
     colors
    2.17
    色的
    2.08
     hues
    2.08
     color
    2.05
     getColor
    2.03
     colours
    2.00
     pigments
    1.93
     اللون
    1.92
     couleurs
    1.83
     colour
    1.81
    Activations Density 2.148%

    No Known Activations