© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77593
    Prev
    Next
    INDEX
    Explanations

    Visual Studio

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

    This neuron detects mentions of specific software products and their version numbers (e.g. “Visual Studio 2012 Express for Windows Desktop”).

    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
     Duf
    -0.80
     beweging
    -0.79
    FileUpload
    -0.77
    nezeu
    -0.77
    ="./
    -0.76
    Resolver
    -0.76
    分数
    -0.72
     subido
    -0.71
    zlich
    -0.71
     ikinci
    -0.71
    POSITIVE LOGITS
     VS
    1.13
     Visual
    1.12
    вець
    0.94
     deven
    0.89
     IDE
    0.82
    Visual
    0.82
    visual
    0.79
    就去
    0.79
     Intelli
    0.76
     VISUAL
    0.76
    Activations Density 0.123%

    No Known Activations