© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8166
    Prev
    Next
    INDEX
    Explanations

    citations with numbers and punctuation

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

    The neuron is triggered by numeric tokens (e.g. reference or measurement 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_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
    <sup>
    0.79
    Notes
    0.67
    Foot
    0.66
    ¹
    0.66
    注
    0.64
    http
    0.63
    footnote
    0.62
    NOTES
    0.61
    ^{
    0.60
    ^[
    0.60
    POSITIVE LOGITS
    nante
    0.68
     infiltr
    0.67
     번째
    0.66
     fokus
    0.66
     incid
    0.65
     ridicul
    0.64
     desesper
    0.64
     detector
    0.63
     ater
    0.63
     nanocom
    0.63
    Activations Density 0.023%

    No Known Activations