© 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. 86466
    Prev
    Next
    INDEX
    Explanations

    man or men

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

    The neuron activates on occurrences of the words “man” or “men,” i.e. explicit mentions of adult males.

    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
    putar
    -1.63
     innych
    -1.63
     empleos
    -1.58
    非常に
    -1.57
     schö
    -1.57
    posição
    -1.55
    kanı
    -1.55
     diputados
    -1.55
     préstamo
    -1.51
     Профиль
    -1.51
    POSITIVE LOGITS
    o
    2.06
    ka
    1.81
    -
    1.77
    va
    1.70
    k
    1.63
    f
    1.62
    de
    1.61
    ︕
    1.60
    mo
    1.58
    man
    1.56
    Activations Density 0.093%

    No Known Activations