© 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. 22-GEMMASCOPE-RES-131K
    7. 14423
    Prev
    Next
    INDEX
    Explanations

    html/css color codes

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

    The neuron fires on hexadecimal color‐code fragments (the hex digits in CSS/HTML style color specifications).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    轍
    -0.94
     sometimes
    -0.94
     Grá
    -0.92
    жом
    -0.91
     Technische
    -0.91
     is
    -0.89
     to
    -0.89
     Úl
    -0.88
     Tecnologia
    -0.88
    핌
    -0.88
    POSITIVE LOGITS
    に似
    1.02
     Лей
    0.99
    glą
    0.99
    感じです
    0.96
     използ
    0.96
     Give
    0.95
    の作成
    0.95
    のである
    0.94
    uhh
    0.94
     colgante
    0.94
    Activations Density 0.004%

    No Known Activations