© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113600
    Prev
    Next
    INDEX
    Explanations

    Windows dot namespace

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

    occurrences of "System.Windows" in C# code, particularly in namespace declarations and using statements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on occurrences of the token “Windows,” e.g. in namespace or type qualifiers like System.Windows.

    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
     samoz
    -2.25
    訁
    -2.22
    癀
    -2.16
    ípio
    -2.11
     TIEMPO
    -2.05
    crania
    -2.00
    u
    -1.99
    anglicky
    -1.98
     отличаются
    -1.98
    ieteur
    -1.97
    POSITIVE LOGITS
    In
    2.48
    “
    2.45
    .
    2.44
    ↵↵
    2.36
    \
    2.30
     sogenannte
    2.25
    <bos>
    2.23
    -
    2.03
    http
    2.02
    ?
    1.99
    Activations Density 0.002%

    No Known Activations