© 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. 10-GEMMASCOPE-RES-131K
    7. 11151
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

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

    The neuron responds to third-person personal pronouns (e.g., he, she, it, they, its).

    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
    llten
    -1.72
    autoreleasepool
    -1.48
     miatt
    -1.45
    ఎ
    -1.45
    thodoxy
    -1.44
    orithmic
    -1.43
     akrab
    -1.41
     ideje
    -1.40
     októ
    -1.38
    PropertyChanging
    -1.38
    POSITIVE LOGITS
     it
    2.59
     its
    1.90
     and
    1.70
     itself
    1.63
     the
    1.48
     based
    1.47
     It
    1.46
     enough
    1.44
     _
    1.36
    它
    1.35
    Activations Density 0.088%

    No Known Activations