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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30936
    Prev
    Next
    INDEX
    Explanations

    Wayne names and places

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

    The neuron fires on occurrences of the proper name “Wayne.”

    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
    Buen
    -0.95
    리고
    -0.84
     fares
    -0.84
    }>
    -0.83
    所能
    -0.82
     potentialities
    -0.82
    strto
    -0.80
     metab
    -0.77
    望着
    -0.76
     ?>/
    -0.76
    POSITIVE LOGITS
    joba
    0.84
     Rooney
    0.79
    lossus
    0.77
    kening
    0.77
    Invalid
    0.77
     Añade
    0.75
    newline
    0.74
    UnitOfWork
    0.73
     saya
    0.73
    ván
    0.71
    Activations Density 0.010%

    No Known Activations