© 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. 53810
    Prev
    Next
    INDEX
    Explanations

    using System;

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

    The neuron strongly activates on C# “using System…” import directives.

    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
    sendFile
    -0.93
    intosh
    -0.87
    负
    -0.70
     various
    -0.69
     Providing
    -0.68
    undy
    -0.68
    Various
    -0.67
     fehér
    -0.67
    žių
    -0.66
    ilado
    -0.66
    POSITIVE LOGITS
    System
    0.91
    Wieder
    0.82
     сериала
    0.81
     System
    0.80
     selezion
    0.79
     scel
    0.78
    ilitar
    0.77
    csharp
    0.77
    Samoa
    0.76
    columnHeader
    0.76
    Activations Density 0.004%

    No Known Activations