© 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. 22-GEMMASCOPE-RES-131K
    7. 130585
    Prev
    Next
    INDEX
    Explanations

    This neuron detects the “et al.” author‐listing marker (the Latin abbreviation indicating additional contributors in copyright or byline blocks).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    lists of contributors or authors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Since
    -0.86
     this
    -0.83
     tipo
    -0.81
    Ọ
    -0.80
     three
    -0.79
     two
    -0.78
     Wä
    -0.78
    slf
    -0.77
    酚
    -0.77
     asal
    -0.76
    POSITIVE LOGITS
     listed
    2.61
    listed
    2.08
    Listed
    1.95
     list
    1.80
     Listed
    1.77
     below
    1.71
    列表
    1.55
    Below
    1.44
     ниже
    1.39
     listes
    1.39
    Activations Density 0.225%

    No Known Activations