© 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. 56854
    Prev
    Next
    INDEX
    Explanations

    Mensa, Mendota, Menachem, Mendoza

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

    The neuron detects occurrences of the character sequence “men” (in any token) – e.g. names or words containing the substring “men.”

    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
     Zü
    -0.74
     Zeug
    -0.74
    toxicity
    -0.69
     quer
    -0.69
    TouchEvent
    -0.68
    ₃
    -0.68
    ガーデン
    -0.68
     directamente
    -0.67
    тит
    -0.66
    Zdra
    -0.66
    POSITIVE LOGITS
    Mods
    0.83
    nymi
    0.80
    érial
    0.78
     alasan
    0.78
     числен
    0.75
     अमे
    0.73
    стта
    0.72
     населення
    0.72
    callable
    0.71
     Wikiquote
    0.71
    Activations Density 0.019%

    No Known Activations