© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6398
    Prev
    Next
    INDEX
    Explanations

    css properties

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

    The neuron fires on CSS declaration keywords—i.e. property names and layout-related terms (like “display,” “grid‐column,” “border‐radius,” etc.).

    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
     ширина
    0.63
    marginLeft
    0.60
     heaped
    0.59
    marginTop
    0.54
    ilizar
    0.54
     '+
    0.53
     Марафон
    0.53
    width
    0.52
     width
    0.52
     '@
    0.52
    POSITIVE LOGITS
    சொ
    0.56
     கலா
    0.55
     ninh
    0.54
     controversy
    0.51
     resear
    0.50
     acontece
    0.50
     intrigue
    0.50
     আর্জেন্ট
    0.49
     abort
    0.49
     *)
    0.48
    Activations Density 0.001%

    No Known Activations