© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3409
    Prev
    Next
    INDEX
    Explanations

    pronouns (they, them, she)

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

    The neuron fires on the slash punctuation in gender‐inclusive pronoun constructions (e.g. “his/her,” “her/him,” “his or her”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     zählen
    0.58
    normals
    0.52
    Five
    0.52
     arası
    0.52
     tük
    0.51
    引发
    0.51
    匏
    0.50
    到底是
    0.49
     showrooms
    0.48
     porphy
    0.48
    POSITIVE LOGITS
     അവളെ
    0.73
     Она
    0.72
     she
    0.71
     frau
    0.70
     그녀
    0.70
     ей
    0.69
     Girl
    0.68
     Jane
    0.68
     她
    0.68
     girl
    0.68
    Activations Density 0.116%

    No Known Activations