© 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. 10-GEMMASCOPE-RES-131K
    7. 1561
    Prev
    Next
    INDEX
    Explanations

    names, bilingual speakers

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

    The neuron specifically activates on occurrences of the name “Khalid” (i.e. the token “Khalid”).

    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
     They
    -3.06
    ,"
    -3.05
     When
    -2.86
     While
    -2.81
     Also
    -2.81
     This
    -2.78
     The
    -2.77
    "
    -2.64
     Now
    -2.63
     It
    -2.56
    POSITIVE LOGITS
     帅气
    2.91
    
    2.75
    淠
    2.67
    姈
    2.64
    猡
    2.59
    馘
    2.50
     colorida
    2.42
     resistente
    2.31
    ⃢
    2.27
     marinho
    2.25
    Activations Density 0.002%

    No Known Activations