© 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. 98175
    Prev
    Next
    INDEX
    Explanations

    C++ using namespace directives

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

    This neuron primarily picks out numeric literals (standalone numbers) in the code.

    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
    pherds
    -0.99
    视着
    -0.85
     Vì
    -0.81
     gemeenten
    -0.79
    нений
    -0.79
    皆さま
    -0.79
    leni
    -0.78
     devido
    -0.77
     due
    -0.77
     に関する
    -0.77
    POSITIVE LOGITS
    using
    1.38
    namespace
    1.37
     using
    1.35
     void
    1.18
     who
    0.91
    $(-
    0.90
     namespace
    0.88
    žo
    0.87
    BEGIN
    0.86
     باستخدام
    0.85
    Activations Density 0.038%

    No Known Activations