© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92600
    Prev
    Next
    INDEX
    Explanations

    socket connections and streams

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

    The neuron fires on code tokens related to socket/SOCKS functionality (e.g. “socket,” “socks,” “PROXY_TYPE_SOCKS5,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     compelling
    -0.87
     external
    -0.85
    斋
    -0.77
     eye
    -0.76
    Abitanti
    -0.73
     längre
    -0.73
    утбу
    -0.73
     lively
    -0.72
     time
    -0.72
     pelig
    -0.71
    POSITIVE LOGITS
    STREAM
    1.20
     STREAM
    1.06
    stream
    1.05
     SOCK
    1.03
     Stream
    1.02
    streaming
    0.98
    Stream
    0.96
    夹
    0.86
     stream
    0.83
    っぱ
    0.79
    Activations Density 0.020%

    No Known Activations