© 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. 10-GEMMASCOPE-RES-131K
    7. 69398
    Prev
    Next
    INDEX
    Explanations

    son of a parent

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

    The neuron detects mentions of family lineage—especially “son of” (or similar) constructions that introduce a person’s parent and their occupation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     to
    -1.97
     will
    -1.73
     more
    -1.71
     if
    -1.63
     different
    -1.47
     people
    -1.43
     some
    -1.35
     smaller
    -1.30
     Wednesday
    -1.29
     get
    -1.25
    POSITIVE LOGITS
     verlangen
    1.47
     Produits
    1.31
    *}{
    1.28
    高达
    1.22
    probably
    1.19
     sánh
    1.19
     who
    1.18
     hombros
    1.16
     Spéc
    1.16
    chenke
    1.13
    Activations Density 0.085%

    No Known Activations