© 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. 38589
    Prev
    Next
    INDEX
    Explanations

    C++ constructs and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Amphi
    -0.79
    Frances
    -0.77
     scottish
    -0.73
     tamil
    -0.73
     OpenAPI
    -0.72
     bacté
    -0.72
     venerdì
    -0.71
     nobis
    -0.70
     jewish
    -0.70
     Kün
    -0.69
    POSITIVE LOGITS
    cpp
    2.47
     cpp
    2.23
    cxx
    1.98
    Cpp
    1.92
    CPP
    1.91
    CXX
    1.88
     CPP
    1.86
    cplusplus
    1.51
     STL
    1.43
    ++
    1.27
    Activations Density 0.455%

    No Known Activations