© 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. 38429
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and family members

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

    The neuron strongly activates on words naming or referring to family relationships and personal pronouns tied to them (e.g. “my,” “mother,” “father,” “brother,” etc.).

    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
    女儿
    -1.88
    Daughter
    -1.69
     hijos
    -1.57
    女兒
    -1.55
     filhos
    -1.46
     figli
    -1.39
     Daughter
    -1.36
    daughter
    -1.35
     zoon
    -1.34
    children
    -1.32
    POSITIVE LOGITS
     parents
    3.80
     mother
    3.39
     father
    3.31
     dad
    2.94
     mom
    2.86
     grandmother
    2.63
     grandfather
    2.56
     Dad
    2.39
     brother
    2.34
     sister
    2.34
    Activations Density 0.060%

    No Known Activations