© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4498
    Prev
    Next
    INDEX
    Explanations

    code delimiters and structure

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

    The neuron activates on numeric tokens that include a decimal point (i.e. floating‐point numbers).

    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
    paginate
    0.80
    및
    0.79
    edition
    0.79
    ByteBuffer
    0.77
    currentPage
    0.76
    Bibliography
    0.75
    tól
    0.75
    찧
    0.75
    proj
    0.74
     новой
    0.74
    POSITIVE LOGITS
    म
    0.88
     confuses
    0.77
     the
    0.77
    न
    0.77
     impeding
    0.75
     sentimientos
    0.73
    يا
    0.71
    足够的
    0.71
    ירות
    0.71
     équipements
    0.69
    Activations Density 0.001%

    No Known Activations