© 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. 128424
    Prev
    Next
    INDEX
    Explanations

    The neuron detects XAML markup‐extension resource references, i.e. tokens in “{StaticResource …}” or “{DynamicResource …}” expressions.

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

    default or standard configurations

    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
     and
    -1.20
    é
    -1.07
     only
    -0.98
    estia
    -0.93
     either
    -0.93
     sometimes
    -0.91
    ique
    -0.91
    D
    -0.91
    pection
    -0.91
     procedures
    -0.90
    POSITIVE LOGITS
     relâche
    1.15
    Klas
    1.10
     default
    1.10
    DEFAULT
    1.10
    معرفی
    1.09
    Tú
    1.08
    default
    1.08
    bkz
    1.06
     стандарт
    1.06
    Kanal
    1.01
    Activations Density 0.033%

    No Known Activations