© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130076
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on the occurrence of the citation shorthand “et al.” in academic references.

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

    et al

    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
     indeb
    -1.07
    リーム
    -1.05
     diverti
    -0.98
     locomo
    -0.97
     lein
    -0.97
     イラストレーション
    -0.96
     zowel
    -0.96
     Detal
    -0.95
     felic
    -0.94
     enfe
    -0.94
    POSITIVE LOGITS
     (
    1.20
     trio
    1.09
     tişört
    1.07
     químicas
    1.05
     jsou
    1.05
    britannien
    1.05
    pagni
    1.05
     armados
    1.05
     decorativos
    1.04
     at
    1.03
    Activations Density 0.009%

    No Known Activations