© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116656
    Prev
    Next
    INDEX
    Explanations

    son or daughter

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

    This neuron specifically detects ordinal lineage or birth‐order terms (e.g. “third,” “eldest”) that mark someone’s rank in a family or succession.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    sibling
    -1.11
    Siblings
    -1.09
    parent
    -1.09
    siblings
    -1.05
     siblings
    -1.05
     grandkids
    -1.05
     Grandmother
    -1.02
     parent
    -1.02
     grandpa
    -1.00
    padre
    -0.99
    POSITIVE LOGITS
     son
    3.50
     daughter
    2.95
     sons
    2.41
     сына
    2.03
    Son
    1.90
    儿子
    1.88
     daughters
    1.87
     Son
    1.83
    息子
    1.82
     сын
    1.81
    Activations Density 0.042%

    No Known Activations