© 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. 1489
    Prev
    Next
    INDEX
    Explanations

    Razor code and ASP.NET syntax

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

    The neuron detects tokens that mark the start of a new line (e.g. newline characters and leading indentation).

    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
    mathcal
    -0.92
    ıyordu
    -0.87
    rakt
    -0.76
    海苔
    -0.74
    血管
    -0.74
     hạn
    -0.73
    냈
    -0.73
    houding
    -0.72
    CONTROL
    -0.71
     rett
    -0.71
    POSITIVE LOGITS
     asp
    0.96
    Razor
    0.93
     razor
    0.88
     Razor
    0.88
     '@
    0.82
    nji
    0.81
     SharePoint
    0.78
     *@
    0.76
    *@
    0.75
    ()=>{
    0.73
    Activations Density 0.013%

    No Known Activations