© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49266
    Prev
    Next
    INDEX
    Explanations

    George precedes surname

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

    The neuron strongly activates on occurrences of the proper name “George.”

    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
     soundtrack
    -0.95
     taha
    -0.94
     konk
    -0.91
     Puis
    -0.91
     sade
    -0.90
    ার
    -0.88
    らい
    -0.87
     tyn
    -0.87
     memer
    -0.85
     facture
    -0.85
    POSITIVE LOGITS
     Washington
    1.25
     Orwell
    1.15
    george
    1.05
    Washington
    1.03
    washington
    1.02
     Clooney
    0.93
    uparrow
    0.87
    NotFound
    0.84
    geti
    0.84
     George
    0.84
    Activations Density 0.013%

    No Known Activations