© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8557
    Prev
    Next
    INDEX
    Explanations

    css properties and styles

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

    The neuron fires on technical identifier tokens—names of CSS properties, HTML attributes, or function/configuration parameter keys.

    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_24_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
    atelier
    0.67
    ۲
    0.65
    اضره
    0.65
    ábbi
    0.64
    อื่น
    0.64
    ۷
    0.63
    koliko
    0.62
    म्मी
    0.61
    reducer
    0.61
    registr
    0.59
    POSITIVE LOGITS
     margin
    0.71
     linewidth
    0.70
     motility
    0.70
     posición
    0.67
     width
    0.66
     positions
    0.65
    %;
    0.64
     culoare
    0.64
     sheared
    0.63
     borderColor
    0.63
    Activations Density 0.092%

    No Known Activations