© 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. 128159
    Prev
    Next
    INDEX
    Explanations

    This neuron detects decorator or annotation syntax (tokens beginning with “@”, such as Angular’s @Component, @View, and @Injectable).

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

    Age as, // Licensed, The present

    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
     to
    -1.33
     και
    -1.14
     medicina
    -1.13
     tehdä
    -1.09
     بعدی
    -1.09
     septembrie
    -1.09
    providedIn
    -1.07
     inginkan
    -1.06
    子さん
    -1.06
    pone
    -1.02
    POSITIVE LOGITS
     vooral
    1.13
     allerdings
    1.12
    ↵↵
    1.12
     azonban
    1.08
     никогда
    1.02
     gingen
    1.02
    Accademia
    1.02
    larımız
    1.00
     usadas
    1.00
     arreg
    1.00
    Activations Density 0.000%

    No Known Activations