© 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. 10-GEMMASCOPE-RES-131K
    7. 43242
    Prev
    Next
    INDEX
    Explanations

    they followed by a verb

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

    The neuron activates on instances of the pronoun “They” (typically at the start of a clause or sentence).

    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
    p
    -3.69
    c
    -3.33
    d
    -3.23
    f
    -3.14
    h
    -3.06
    b
    -3.00
    s
    -2.97
    k
    -2.89
    a
    -2.88
    u
    -2.83
    POSITIVE LOGITS
    They
    4.88
    Their
    3.67
    There
    3.19
    It
    3.11
    Then
    2.86
    You
    2.64
    Some
    2.59
    Those
    2.59
    These
    2.56
    Its
    2.56
    Activations Density 0.009%

    No Known Activations