© 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. 127669
    Prev
    Next
    INDEX
    Explanations

    The neuron detects mentions of Native American heritage—specifically phrases stating someone is “part Native American.”

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    family and people relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    omethane
    -1.06
    レディース
    -1.02
    ジャケット
    -0.98
    一听
    -0.95
    どれも
    -0.93
    fancybox
    -0.91
    这般
    -0.91
    ブログ村
    -0.91
     Soccerway
    -0.90
    ブーツ
    -0.89
    POSITIVE LOGITS
     two
    1.45
     other
    1.35
     three
    1.15
     family
    1.10
     younger
    1.09
     friends
    1.09
     brother
    1.07
     sister
    1.05
     older
    1.05
     four
    0.98
    Activations Density 0.031%

    No Known Activations