© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1707
    Prev
    Next
    INDEX
    Explanations

    parental figures and family relations

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

    The neuron fires on occurrences of the word “father.”

    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
    i
    0.83
    ل
    0.75
    t
    0.73
     irritated
    0.72
    y
    0.71
    b
    0.71
    ن
    0.71
     complained
    0.68
    m
    0.68
    ED
    0.67
    POSITIVE LOGITS
    ة
    0.86
    시킨
    0.79
    辈
    0.79
    ം
    0.78
     ਅਤੇ
    0.77
    ductory
    0.75
    zeitig
    0.75
    祖
    0.72
    generational
    0.72
    曾在
    0.72
    Activations Density 0.000%

    No Known Activations