© 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. 119065
    Prev
    Next
    INDEX
    Explanations

    tcp socket connect

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    httpd
    -0.96
    ServerSocket
    -0.96
    projekt
    -0.88
    UPLOAD
    -0.84
    的食物
    -0.79
    server
    -0.79
     Http
    -0.78
    <0xC8>
    -0.78
    Committed
    -0.77
     Server
    -0.75
    POSITIVE LOGITS
     connect
    1.36
     connecting
    1.20
     Connect
    1.18
    Connect
    1.16
    connect
    1.09
     tried
    1.01
     tries
    0.90
     Connecting
    0.88
    Connecting
    0.86
     连接
    0.84
    Activations Density 0.034%

    No Known Activations