© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3343
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on tokens that are parts of person names (initials, surnames, or full first names) in author or contributor lists.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     handleError
    0.79
    yatiti
    0.69
     ilişk
    0.67
    <unused22>
    0.67
     errorMessage
    0.67
    <unused28>
    0.64
     clickView
    0.64
     SQLException
    0.63
     Paryayvachi
    0.63
    <unused66>
    0.62
    POSITIVE LOGITS
    等等
    0.61
    misc
    0.59
    ↵
    0.56
    ↵↵↵
    0.56
    单纯
    0.55
     various
    0.52
    各种
    0.52
    various
    0.50
    Կ
    0.50
    睑
    0.49
    Activations Density 0.507%

    No Known Activations