© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 69988
    Prev
    Next
    INDEX
    Explanations

    et al

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

    This neuron detects occurrences of the citation marker “et al.” in reference lists.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     what
    -1.31
     both
    -1.18
     which
    -1.07
     should
    -1.07
     kedua
    -1.04
     about
    -0.97
     by
    -0.96
     répondit
    -0.95
     Unterhaltung
    -0.95
     before
    -0.95
    POSITIVE LOGITS
    .,
    1.10
     myster
    0.97
     dismal
    0.95
    lai
    0.95
    ła
    0.92
    IVING
    0.91
     painters
    0.91
    lare
    0.90
     ines
    0.90
    viruses
    0.90
    Activations Density 0.013%

    No Known Activations