© 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. 34-GEMMASCOPE-RES-131K
    7. 1609
    Prev
    Next
    INDEX
    Explanations

    hex colors and codes

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

    This neuron detects hexadecimal digit tokens in code, especially in CSS/HTML color‐code strings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    #
    -1.16
     give
    -0.92
     When
    -0.84
    []
    -0.81
     controla
    -0.81
    }
    -0.79
    _;
    -0.78
     six
    -0.77
    ;
    -0.77
     these
    -0.76
    POSITIVE LOGITS
     Вале
    1.02
     ۰
    0.96
    ירים
    0.95
     réfrigérateur
    0.95
    losseum
    0.95
    eait
    0.94
     captivating
    0.94
    Хочу
    0.93
     iluminação
    0.93
     forêts
    0.90
    Activations Density 0.007%

    No Known Activations