© 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. 45377
    Prev
    Next
    INDEX
    Explanations

    extended family members

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

    The neuron fires on kinship terms and living‐with family arrangements (e.g. uncle, aunt, grandparents, nephew, live with).

    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
    Daughter
    -1.04
     daughter
    -0.98
    儿子
    -0.98
     hijo
    -0.98
    妹妹
    -0.94
     сын
    -0.89
     Daughter
    -0.87
    媳妇
    -0.85
    tagonal
    -0.85
    daughter
    -0.85
    POSITIVE LOGITS
     uncle
    4.53
     aunt
    4.13
     Uncle
    3.94
     Aunt
    3.75
     uncles
    3.67
     aunts
    3.66
    Uncle
    3.63
    uncle
    3.55
    Aunt
    3.23
    aunt
    2.73
    Activations Density 0.029%

    No Known Activations