© 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. 10303
    Prev
    Next
    INDEX
    Explanations

    .com, .de, .org websites

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

    This neuron detects reference and citation markers, such as URLs, DOIs, ISBNs, and other numeric or domain tokens in bibliographic entries.

    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
    monday
    0.79
    fichier
    0.72
    gpio
    0.71
    filepath
    0.70
    文
    0.70
    blogspot
    0.68
    cdr
    0.68
    諰
    0.68
    独特
    0.67
    λλά
    0.66
    POSITIVE LOGITS
     com
    0.86
     Friends
    0.72
     Deus
    0.71
     memorabilia
    0.70
     Ně
    0.70
     Hotspur
    0.69
     vua
    0.69
     João
    0.68
     Freunde
    0.68
     Yacht
    0.66
    Activations Density 0.038%

    No Known Activations