© 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. 127853
    Prev
    Next
    INDEX
    Explanations

    This neuron detects personal names (proper names of people).

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

    names of people

    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
     their
    -1.13
    честве
    -1.13
    ffekt
    -1.07
    resiasi
    -1.04
    ΤΟ
    -1.04
    Portály
    -1.03
    bourhood
    -1.01
    텐츠
    -0.98
    ministrazione
    -0.98
    ısında
    -0.97
    POSITIVE LOGITS
     who
    1.77
     is
    1.28
     recently
    1.24
    It
    1.20
    Like
    1.20
     was
    1.09
    According
    1.05
    刚刚
    1.01
    Unlike
    1.00
    是一款
    1.00
    Activations Density 0.052%

    No Known Activations