© 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. 5289
    Prev
    Next
    INDEX
    Explanations

    autism, 😊, value, charming

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

    This neuron detects mentions of the phrase “men and women,” i.e. explicit references to a mixed-gender audience.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    er
    0.87
    ta
    0.80
    MUX
    0.80
    то
    0.77
    o
    0.73
    fou
    0.71
    M
    0.70
    U
    0.70
    вання
    0.70
    lez
    0.68
    POSITIVE LOGITS
    ुरू
    0.85
     Tets
    0.84
     เจ้า
    0.76
     Narcotics
    0.75
     Committee
    0.74
     bộ
    0.74
     Tiến
    0.73
     Jamal
    0.73
     khủng
    0.73
     Magistrate
    0.73
    Activations Density 0.000%

    No Known Activations