© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128282
    Prev
    Next
    INDEX
    Explanations

    This neuron is detecting namespace import tokens from the Windows/.NET UI and related libraries (e.g. “Windows”, UI, Xaml, Media, Forms, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    System.Windows.Xaml

    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_22/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
    の方も
    -1.81
    に入れる
    -1.80
    に入れ
    -1.78
    にします
    -1.69
     their
    -1.63
    に来
    -1.63
    のご紹介
    -1.59
    に行って
    -1.58
    の人は
    -1.55
    に行きました
    -1.54
    POSITIVE LOGITS
    があり
    1.83
    などが
    1.53
     {},
    1.44
    がありますが
    1.43
    などを
    1.35
    ebly
    1.34
     [],
    1.33
    <bos>
    1.33
    ztes
    1.31
    があります
    1.28
    Activations Density 0.006%

    No Known Activations