© 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. 68165
    Prev
    Next
    INDEX
    Explanations

    Tracy followed by a surname

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

    The neuron selectively activates on occurrences of the proper name “Tracy.”

    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
    理工
    -2.47
    henswürdigkeiten
    -2.42
    FORMAN
    -2.41
    ᎑
    -2.36
    IANGLES
    -2.34
    埽
    -2.31
    燠
    -2.30
     With
    -2.30
    OUTUBE
    -2.27
    三月
    -2.25
    POSITIVE LOGITS
    4
    3.27
    0
    3.11
    6
    2.97
    i
    2.89
    5
    2.88
    3
    2.86
     "
    2.81
    8
    2.78
    s
    2.66
    .
    2.55
    Activations Density 0.011%

    No Known Activations