© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7294
    Prev
    Next
    INDEX
    Explanations

    border and related CSS properties

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

    The neuron strongly activates on CSS property identifiers—especially hyphenated property names like “border-radius,” “background-position,” and similar tokens.

    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_31_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
     절대
    0.61
    uiDesigner
    0.59
    >©
    0.58
     poesía
    0.55
    ्यर
    0.55
    objectif
    0.54
     titulares
    0.54
    戕
    0.54
    ሪ
    0.53
    ﻩ
    0.53
    POSITIVE LOGITS
     border
    0.85
     borderColor
    0.84
     Border
    0.83
    borderColor
    0.78
    border
    0.71
     Solid
    0.71
     borders
    0.71
     Borders
    0.71
     solid
    0.70
    Border
    0.70
    Activations Density 0.023%

    No Known Activations