© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1322
    Prev
    Next
    INDEX
    Explanations

    The neuron detects archival‐citation metadata in references (e.g. “Wayback Machine,” “archived from the original,” archive dates).

    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
    :
    1.10
     =
    1.01
    ↵
    0.96
    ,
    0.95
    -
    0.93
    .
    0.89
    0.89
    _
    0.85
    =
    0.82
     -
    0.79
    POSITIVE LOGITS
    <unused77>
    0.89
     وړیا
    0.88
    <unused11>
    0.87
    ळख
    0.86
    <unused57>
    0.84
     وګټ
    0.84
     زاويه
    0.83
    <unused55>
    0.82
     आरमारा
    0.80
     پیسو
    0.80
    Activations Density 0.000%

    No Known Activations