© 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. 5064
    Prev
    Next
    INDEX
    Explanations

    "use", "ties", "with", "using", "Halloween"

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

    This neuron detects numeric tokens that appear as bibliographic reference identifiers (e.g. volume, issue, and page numbers in citations).

    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
    ן
    0.91
    mu
    0.86
     Hak
    0.79
     Ceremon
    0.77
     CLAIM
    0.77
     etti
    0.77
    ը
    0.76
    τι
    0.75
     آگے
    0.75
    abhavam
    0.75
    POSITIVE LOGITS
    SY
    0.75
    બા
    0.74
    ຼ
    0.73
    初心
    0.73
    iva
    0.72
    LP
    0.71
    的数据
    0.70
     chickens
    0.70
    WY
    0.70
    НУ
    0.69
    Activations Density 0.001%

    No Known Activations