© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13420
    Prev
    Next
    INDEX
    Explanations

    parenting and birth

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

    The neuron fires on mentions of family relationships and life‐events, especially motherhood and children (e.g. “mother,” “daughter,” “baby,” “child,” “born”).

    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_24_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
     shirtless
    0.75
     इस्तेमाल
    0.71
    ዳል
    0.71
    錆
    0.71
    on
    0.70
     points
    0.70
     résistance
    0.70
     دوستان
    0.69
    points
    0.69
     amigo
    0.68
    POSITIVE LOGITS
     dziecka
    1.98
     ребенка
    1.92
    孩子
    1.89
    👪
    1.85
    👶
    1.84
    🤱
    1.83
     hijos
    1.78
     parenting
    1.78
    孩子的
    1.77
     فرزند
    1.76
    Activations Density 1.596%

    No Known Activations