© 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. 65434
    Prev
    Next
    INDEX
    Explanations

    Joshua followed by a name

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

    The neuron strongly detects occurrences of the personal name “Joshua.”

    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
     обеспечивает
    -2.58
     The
    -2.34
    //'
    -2.28
     '
    -2.23
    ">
    -2.20
     คือ
    -2.16
     kreeg
    -2.13
     eventual
    -2.11
    
    -2.08
     meinem
    -2.05
    POSITIVE LOGITS
    $
    2.66
    also
    2.55
    1
    2.38
    ,“
    2.28
    The
    2.27
    行って
    2.25
    “
    2.14
    驁
    2.13
    In
    2.08
    闥
    2.03
    Activations Density 0.006%

    No Known Activations