© 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. 10-GEMMASCOPE-RES-131K
    7. 40419
    Prev
    Next
    INDEX
    Explanations

    Sandra followed by surname

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

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

    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
    谖
    -2.73
    崀
    -2.33
     interruption
    -2.28
    鶿
    -2.23
    🤱
    -2.20
     impediment
    -2.14
     utilisons
    -2.14
    ć
    -2.06
    !”
    -2.05
     نقطة
    -2.03
    POSITIVE LOGITS
    猡
    2.39
    咴
    2.38
     terwijl
    2.33
    舠
    2.19
     They
    2.08
     yakni
    2.06
    
    2.03
    ي
    2.03
    龃
    2.03
    鏵
    1.96
    Activations Density 0.000%

    No Known Activations