© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11342
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on mentions of CSS class-related terminology (e.g., “CSS classes,” “.scss,” styling code references).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ق
    0.91
    Foreground
    0.88
    ب
    0.87
    controllers
    0.86
     обязан
    0.86
    व
    0.86
    控制器
    0.85
    ف
    0.84
    Hardware
    0.80
    Automat
    0.80
    POSITIVE LOGITS
     stylist
    1.45
     stylists
    1.36
     styling
    1.30
     CSS
    1.23
     styled
    1.23
     stylesheet
    1.21
     css
    1.20
     Css
    1.19
     stylesheets
    1.16
     hairst
    1.05
    Activations Density 0.081%

    No Known Activations