© 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. 31-GEMMASCOPE-2-RES-16K
    4. 8424
    Prev
    Next
    INDEX
    Explanations

    css properties

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

    This neuron activates on code‐style tokens and technical identifiers—things like file paths, CSS class names, HTML/JS element names, URLs, and other snippet-like strings.

    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
     marginTop
    0.64
    ப்பாடு
    0.58
    ocumented
    0.57
     nonEmpty
    0.56
    </tfoot>
    0.55
     benthic
    0.55
     UIAlert
    0.55
    ாஹ்
    0.53
     cyan
    0.52
     enabled
    0.52
    POSITIVE LOGITS
    Flex
    0.53
    flex
    0.53
     Flex
    0.52
     flex
    0.51
    MediaQuery
    0.51
    img
    0.50
    Img
    0.48
    NFT
    0.48
    Sunflower
    0.48
    🫶
    0.48
    Activations Density 0.000%

    No Known Activations