© 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. 106395
    Prev
    Next
    INDEX
    Explanations

    pat, dan, bob, stan, bill

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

    The neuron is detecting personal names (proper first names) 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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     John
    -0.92
     populares
    -0.88
    Ϣ
    -0.88
     отли
    -0.87
     untuk
    -0.84
     Dinamarca
    -0.83
    捗
    -0.81
     siete
    -0.81
    codings
    -0.81
     için
    -0.79
    POSITIVE LOGITS
    釙
    1.13
    裃
    1.03
    sie
    1.03
    ie
    1.02
    又是一
    0.98
    我真的
    0.97
    Andrés
    0.97
     abbandon
    0.96
    Zé
    0.96
    ny
    0.94
    Activations Density 0.077%

    No Known Activations