© 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. 34-GEMMASCOPE-RES-131K
    7. 64750
    Prev
    Next
    INDEX
    Explanations

    css height attributes

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

    The neuron detects CSS/HTML style syntax, i.e. selectors and property‐declaration tokens (e.g. “html”, “body”, “height”, “{”, “:”, “%”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     width
    -1.27
     widths
    -1.13
    宽度
    -1.04
    Width
    -1.03
     Width
    -0.95
     шири
    -0.94
    width
    -0.93
    WIDTH
    -0.92
     WIDTH
    -0.91
    MaxWidth
    -0.87
    POSITIVE LOGITS
    vh
    1.13
     vh
    1.08
    minHeight
    1.05
     HEIGHT
    0.98
     height
    0.98
     Height
    0.94
    height
    0.89
    screen
    0.89
     getHeight
    0.89
     taller
    0.87
    Activations Density 0.023%

    No Known Activations