© 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. 10-GEMMASCOPE-RES-131K
    7. 38802
    Prev
    Next
    INDEX
    Explanations

    hex color codes

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

    The neuron activates on the numeric characters that appear in hexadecimal color codes (the hex‐digit sequences in CSS/markup color definitions).

    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
     will
    -1.68
    我们在
    -1.34
     would
    -1.32
    We
    -1.30
     cinque
    -1.24
     not
    -1.23
     полка
    -1.22
    𐄙
    -1.22
     could
    -1.20
     sóc
    -1.20
    POSITIVE LOGITS
     Atención
    1.20
     ergo
    1.13
    чном
    1.10
    "$_
    1.09
     unequiv
    1.09
     imme
    1.08
     ayur
    1.08
    edits
    1.07
     accep
    1.06
     discer
    1.06
    Activations Density 0.028%

    No Known Activations