© 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. 34-GEMMASCOPE-RES-131K
    4. 37826
    Prev
    Next
    INDEX
    Explanations

    CSS at-rules and imports

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

    The neuron specifically fires on CSS at-rule declarations (tokens beginning with “@,” e.g. @keyframes, @media, @import, etc.).

    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
     Sundays
    -0.81
    Barre
    -0.79
     classrooms
    -0.78
    wiesen
    -0.77
     камень
    -0.76
    Cookies
    -0.75
     jardin
    -0.75
    Etienne
    -0.74
    cookies
    -0.74
     respira
    -0.73
    POSITIVE LOGITS
     media
    1.06
    keyframes
    1.06
    media
    0.96
     rules
    0.93
    charset
    0.91
     rule
    0.89
    import
    0.88
     key
    0.81
    ryn
    0.79
    Supporting
    0.78
    Activations Density 0.017%

    No Known Activations