© 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. 70162
    Prev
    Next
    INDEX
    Explanations

    CSS hidden and center properties

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

    This neuron detects CSS property values used for layout and visibility control—things like positioning (absolute/relative), overflow settings (hidden), display modes (none, block, inline-block, table), and alignment (center).

    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
     So
    -2.00
     have
    -1.92
    es
    -1.82
    vi
    -1.80
     I
    -1.80
     o
    -1.77
     d
    -1.77
          
    -1.77
     is
    -1.75
     <
    -1.75
    POSITIVE LOGITS
    .
    2.80
    
    2.00
     formulaire
    1.74
    酲
    1.73
    🔣
    1.73
    *'
    1.70
     BRIG
    1.67
     FLOR
    1.66
     and
    1.66
     vinyle
    1.65
    Activations Density 0.012%

    No Known Activations