© 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. 10-GEMMASCOPE-RES-131K
    7. 130644
    Prev
    Next
    INDEX
    Explanations

    Xaml, CodeAnalysis, .NET

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

    The neuron is triggered by occurrences of the term “Xaml” (i.e. references to XAML namespaces or types).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    𓄹
    -3.09
    er
    -2.89
    に
    -2.53
    ⩩
    -2.53
    缐
    -2.45
    s
    -2.44
     digitais
    -2.44
    鉝
    -2.41
    暻
    -2.38
     DÍA
    -2.30
    POSITIVE LOGITS
     diseñ
    2.39
     
    2.23
     básicamente
    2.19
    )
    2.16
     mélang
    2.16
     reconoc
    2.08
    <em>
    2.08
    ,
    2.05
     verdaderamente
    2.03
    </h3>
    2.02
    Activations Density 0.002%

    No Known Activations