© 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. 34-GEMMASCOPE-RES-131K
    7. 31722
    Prev
    Next
    INDEX
    Explanations

    Xaml, regex, .dll, Channel

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

    This neuron responds to technical identifiers in code, especially dot-separated namespace or API names (e.g. “Windows.UI.Xaml”).

    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
     याद
    -0.71
    lawn
    -0.68
    trace
    -0.68
     ім
    -0.66
    المنا
    -0.65
     trace
    -0.65
    計画
    -0.63
    flan
    -0.63
     Trace
    -0.62
     islanders
    -0.62
    POSITIVE LOGITS
    主張
    0.75
    reti
    0.68
     SAA
    0.66
     popcorn
    0.65
    Avo
    0.65
    BOY
    0.64
    peut
    0.64
     Fram
    0.64
    adak
    0.64
    蜱
    0.64
    Activations Density 0.092%

    No Known Activations