© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5641
    Prev
    Next
    INDEX
    Explanations

    css padding and border

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

    The neuron detects CSS property keywords (especially “background” and “border”) indicating style declarations.

    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
    ক
    0.73
    ي
    0.72
    Maximum
    0.71
     Août
    0.70
    क
    0.69
    นี่
    0.68
    นอก
    0.64
     Maximum
    0.63
    นัก
    0.63
    मैं
    0.62
    POSITIVE LOGITS
     aspectRatio
    0.76
     borderColor
    0.75
     border
    0.74
     repeatable
    0.67
     infraction
    0.66
     sketched
    0.65
     допомогою
    0.65
    Ⴀ
    0.65
    璧
    0.64
     Gabriele
    0.63
    Activations Density 0.000%

    No Known Activations