© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6166
    Prev
    Next
    INDEX
    Explanations

    genealogy and family history

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

    This neuron fires on document metadata and structured elements—dates, section numbers, time‐frame labels, statistical figures, and formal headings.

    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
     getConfig
    0.66
     gomme
    0.65
    uniqueItems
    0.64
     goma
    0.62
     Yogurt
    0.62
     espuma
    0.61
     exoskeleton
    0.60
    狞
    0.60
     pavimento
    0.59
     headband
    0.58
    POSITIVE LOGITS
     genealogical
    1.95
     genealog
    1.84
     genealogy
    1.72
     Genealogical
    1.66
     Ancest
    1.56
    Ancest
    1.53
     Genealogy
    1.53
     ancestry
    1.52
     ancestor
    1.32
     ancestors
    1.31
    Activations Density 0.403%

    No Known Activations