© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13033
    Prev
    Next
    INDEX
    Explanations

    series

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

    The neuron detects tokens that are part of bibliographic citations and reference strings (e.g. titles, authors, publication info).

    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
    xiety
    0.69
    bilisi
    0.69
    <unused963>
    0.68
    <0x18>
    0.67
    ctuations
    0.64
     passwd
    0.64
     온라인
    0.63
    icosia
    0.63
    rescence
    0.63
    ucalyptus
    0.62
    POSITIVE LOGITS
    )|
    1.77
     series
    1.20
     Series
    1.04
    シリーズ
    1.03
    )
    1.01
     séries
    0.95
    系列
    0.93
    )[
    0.91
    !)
    0.91
    )|\
    0.91
    Activations Density 0.007%

    No Known Activations