© 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. 10-GEMMASCOPE-RES-131K
    7. 101010
    Prev
    Next
    INDEX
    Explanations

    palette or pallet

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

    The neuron activates on words referring to visual color samples or palettes (e.g., “palette,” “pal,” “swatch”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Instead
    -2.23
     Rather
    -2.09
    j
    -2.00
     Ideally
    -1.97
     Initially
    -1.92
     letzten
    -1.91
     Indeed
    -1.91
    鬭
    -1.88
     Whereas
    -1.87
     Essentially
    -1.85
    POSITIVE LOGITS
    '
    1.98
    /***/
    1.88
    .'
    1.84
    mannian
    1.84
    rensa
    1.80
    🪤
    1.80
     Japão
    1.78
     CURLOPT
    1.77
     juiz
    1.77
    .?
    1.75
    Activations Density 0.004%

    No Known Activations