© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62567
    Prev
    Next
    INDEX
    Explanations

    his or her

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

    The neuron is activated by third‐person masculine pronouns (e.g. “his,” “him,” “he”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    reportWebVitals
    -1.22
    glEnable
    -1.18
     endregion
    -1.16
    glClear
    -1.15
    co
    -1.15
     “
    -1.12
    mapStateToProps
    -1.12
    罐
    -1.11
    vasive
    -1.11
    #:
    -1.10
    POSITIVE LOGITS
     or
    4.66
    /
    2.11
     his
    1.88
    หรือ
    1.72
    或
    1.70
     или
    1.58
     kiezen
    1.48
     she
    1.48
     bzw
    1.36
    OrUpdate
    1.34
    Activations Density 0.019%

    No Known Activations