© 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. 4466
    Prev
    Next
    INDEX
    Explanations

    citations and research papers

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

    The neuron sharply activates on standalone numeric tokens in reference citations—e.g. volume, issue, page, and year 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
     unpublished
    0.75
     Unpublished
    0.71
     monograph
    0.70
    ee
    0.69
    preprint
    0.68
    a
    0.67
     makalah
    0.63
    ॅ
    0.61
     untersucht
    0.60
    unpublished
    0.59
    POSITIVE LOGITS
    自分の
    0.74
     scams
    0.73
    用の
    0.68
    詐
    0.67
     можете
    0.66
    雞
    0.66
     conspiracies
    0.66
    奶
    0.64
     termite
    0.64
     могу
    0.64
    Activations Density 0.025%

    No Known Activations