© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100427
    Prev
    Next
    INDEX
    Explanations

    their or they followed by a verb

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

    The neuron activates on occurrences of the pronoun “they.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     only
    -2.50
     for
    -2.20
    </em>
    -1.93
     from
    -1.91
     their
    -1.81
     which
    -1.71
    Only
    -1.66
     από
    -1.54
     adequate
    -1.53
     slightly
    -1.48
    POSITIVE LOGITS
     then
    1.53
    fasst
    1.52
    warzys
    1.46
     alrededores
    1.44
    itores
    1.42
     mismos
    1.41
    受欢迎
    1.39
    KommentareTeilen
    1.38
    iales
    1.38
    owanie
    1.38
    Activations Density 0.057%

    No Known Activations