© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35644
    Prev
    Next
    INDEX
    Explanations

    HTML/CSS selectors and declarations

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

    The neuron fires on HTML/CSS styling declarations—especially border, background‐color, and other visual attribute settings.

    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
     to
    -1.03
     or
    -1.01
     Kruse
    -0.83
    💁
    -0.83
     것입니다
    -0.83
     йо
    -0.79
     gree
    -0.78
    oga
    -0.78
    '
    -0.77
    ните
    -0.77
    POSITIVE LOGITS
     mercancías
    1.14
     Anzeigen
    1.13
     botões
    1.10
     containing
    1.08
     picioare
    1.07
    ventilated
    1.05
    溷
    1.05
     confirmación
    1.04
     continuidad
    1.04
     berisi
    1.04
    Activations Density 0.005%

    No Known Activations