© 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. 10-GEMMASCOPE-RES-131K
    7. 83879
    Prev
    Next
    INDEX
    Explanations

    fernando or franciscans and surnames

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

    The neuron detects occurrences of the proper name “Fernando.”

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     in
    -2.48
     and
    -2.47
    鬭
    -2.38
    蔸
    -2.34
    ffled
    -2.20
    鴴
    -2.19
    这只
    -2.16
     caminh
    -2.14
    呓
    -2.14
    蹋
    -2.11
    POSITIVE LOGITS
    v
    2.91
    In
    2.56
    ”
    2.50
    4
    2.48
    ”،
    2.45
    n
    2.44
    Contrary
    2.42
    The
    2.28
    ほんとに
    2.27
     unmatched
    2.25
    Activations Density 0.003%

    No Known Activations