© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3598
    Prev
    Next
    INDEX
    Explanations

    masculine names following family terms

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

    The neuron detects kinship terms—words naming family relationships (e.g. brother, sister, daughter, son, twin, siblings).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     Worcestershire
    -0.86
     riffs
    -0.77
     Zeppelin
    -0.75
     iterable
    -0.75
    JButton
    -0.74
     joseph
    -0.74
     Maximilian
    -0.74
     Isabella
    -0.73
    ului
    -0.73
    addPreferredGap
    -0.73
    POSITIVE LOGITS
     Gary
    1.16
     Kevin
    1.10
     Ryan
    1.07
     Brian
    1.05
     Keith
    1.04
     Daryl
    1.03
     Craig
    1.02
     Bryan
    0.99
     Cheryl
    0.98
     Greg
    0.98
    Activations Density 0.006%

    No Known Activations