© 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. 22-GEMMASCOPE-RES-131K
    7. 73635
    Prev
    Next
    INDEX
    Explanations

    network listening and accepting connections

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

    This neuron responds to low‐level socket‐programming calls and parameters, i.e. mentions of functions like accept, listen, connect/recv and associated port or length arguments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    naments
    -1.15
    这些
    -1.05
    theore
    -1.00
    𝑈
    -1.00
    orial
    -1.00
    OBJETIVO
    -0.99
     madu
    -0.96
    −/−
    -0.94
     membri
    -0.94
    peted
    -0.94
    POSITIVE LOGITS
     waiting
    1.40
     await
    1.13
     awaits
    1.11
     waits
    1.10
     after
    1.10
     wait
    1.09
     while
    1.06
     first
    1.06
     thereafter
    1.02
     just
    1.01
    Activations Density 0.012%

    No Known Activations