© 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. 34-GEMMASCOPE-RES-131K
    7. 79106
    Prev
    Next
    INDEX
    Explanations

    client and server

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

    This neuron identifies programming code snippets, especially lines with include directives and other source‐code tokens.

    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
    機種
    -0.87
    トーン
    -0.81
    そも
    -0.80
    DebuggerStep
    -0.80
     getAccount
    -0.79
    Medal
    -0.79
    事です
    -0.79
     kanskje
    -0.78
    лися
    -0.77
     lachen
    -0.77
    POSITIVE LOGITS
     client
    2.94
     clients
    2.33
    client
    2.11
     Client
    1.91
     Clients
    1.82
     server
    1.80
    Client
    1.77
    CLIENT
    1.75
    clients
    1.74
    客户端
    1.70
    Activations Density 0.106%

    No Known Activations