© 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. 34515
    Prev
    Next
    INDEX
    Explanations

    Jamie or Jaime names

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

    This neuron detects occurrences of the personal name “Jamie” (and close variants thereof).

    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
    変な
    -0.97
     unknown
    -0.93
     využ
    -0.90
    うまい
    -0.89
    他就
    -0.89
     desconhe
    -0.87
    地味
    -0.86
     большим
    -0.85
    textsc
    -0.85
     descobri
    -0.85
    POSITIVE LOGITS
    🤯
    0.96
    昵称
    0.96
    Jamie
    0.92
     Lynn
    0.89
    Lynn
    0.86
    靑
    0.85
    斯的
    0.84
    ｅ
    0.84
    ིག་
    0.84
     Jamie
    0.84
    Activations Density 0.006%

    No Known Activations