© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75496
    Prev
    Next
    INDEX
    Explanations

    background css properties

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

    The neuron strongly activates on occurrences of the CSS “background” property (e.g. “background-…” declarations).

    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
    jede
    -0.95
    ných
    -0.85
     Nhưng
    -0.79
    yout
    -0.79
    酌
    -0.77
    ﾍ
    -0.76
    PickerController
    -0.76
     what
    -0.75
    belea
    -0.75
    蔭
    -0.74
    POSITIVE LOGITS
     background
    1.34
     color
    1.17
    background
    1.15
    背景
    1.10
    color
    1.09
     màu
    1.07
    Background
    1.06
    Color
    1.02
     colour
    1.01
    BACKGROUND
    0.99
    Activations Density 0.005%

    No Known Activations