© 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. 22-GEMMASCOPE-RES-131K
    7. 25178
    Prev
    Next
    INDEX
    Explanations

    names of family and associates

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

    This neuron detects mentions of family relationships (e.g. husband, son, twin, sister) in the text.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     MyBatis
    -1.77
    踯
    -1.77
    iiii
    -1.73
    姈
    -1.72
     Dinas
    -1.71
    菒
    -1.68
    ⃰
    -1.64
    牁
    -1.64
     Sistema
    -1.63
    iiiii
    -1.63
    POSITIVE LOGITS
     and
    2.80
     from
    2.17
     three
    2.09
     two
    2.08
     with
    2.06
     like
    2.05
     four
    2.02
     will
    1.98
     including
    1.96
     five
    1.90
    Activations Density 0.003%

    No Known Activations