© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50384
    Prev
    Next
    INDEX
    Explanations

    women and titles

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

    The neuron is strongly activated by the capitalized word “Women,” marking occurrences of that token in the text.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    localVar
    -0.75
    eski
    -0.73
     деньги
    -0.68
     Mog
    -0.66
     sqm
    -0.66
     草
    -0.66
     permisos
    -0.66
    pture
    -0.66
     Оста
    -0.66
     resol
    -0.65
    POSITIVE LOGITS
    YesNo
    0.68
     nell
    0.66
     Globals
    0.65
     holland
    0.63
    心地
    0.62
     BLL
    0.62
     maneuvering
    0.61
     монтажа
    0.61
     ortak
    0.61
    цо
    0.61
    Activations Density 0.068%

    No Known Activations