© 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. 102824
    Prev
    Next
    INDEX
    Explanations

    socket or connection context

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

    the word "Socket" in programming code, particularly in class names, imports, and API references.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron detects occurrences of the (capitalized) word “Socket” in code or error messages.

    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
     
    -3.97
    “
    -2.97
    d
    -2.94
    b
    -2.72
     "
    -2.56
    section
    -2.50
    le
    -2.48
    「
    -2.44
    A
    -2.41
    2
    -2.33
    POSITIVE LOGITS
    ي
    2.77
    瀦
    2.63
     жовтня
    2.58
    呓
    2.58
     शुर
    2.58
    轰隆
    2.55
    ⼭
    2.45
    
    2.44
    啬
    2.44
    會議
    2.44
    Activations Density 0.001%

    No Known Activations