© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100958
    Prev
    Next
    INDEX
    Explanations

    css border and shadow

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

    the word "border" in CSS code or HTML/CSS styling contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects CSS property names (especially “border” variants and “box-shadow”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ⎔
    -1.82
    𓁹
    -1.66
     decidedly
    -1.63
    蓠
    -1.61
     ridiculously
    -1.59
     lauded
    -1.47
     serene
    -1.44
    ='';
    -1.42
     delightfully
    -1.42
     strikingly
    -1.40
    POSITIVE LOGITS
     and
    2.16
    www
    1.69
     with
    1.69
    You
    1.63
    Taking
    1.60
     by
    1.53
    Many
    1.53
    There
    1.52
    Since
    1.52
    Going
    1.51
    Activations Density 0.004%

    No Known Activations