© 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. 10-GEMMASCOPE-RES-131K
    7. 58778
    Prev
    Next
    INDEX
    Explanations

    julie followed by other names

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

    The neuron specifically activates on occurrences of the proper name “Julie.”

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

    No Comments

    Negative Logits
    各样的
    -2.47
    ’
    -2.28
     丁目
    -2.23
    牁
    -2.19
     voor
    -2.17
    ৹
    -2.13
    nicht
    -2.11
    旆
    -2.11
     '
    -2.11
    colgante
    -2.09
    POSITIVE LOGITS
     defies
    2.59
    榈
    2.48
    垍
    2.47
    先は
    2.39
     denies
    2.38
     opted
    2.38
    jewództ
    2.36
    vantaged
    2.34
     joked
    2.34
     was
    2.33
    Activations Density 0.004%

    No Known Activations