© 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. 128732
    Prev
    Next
    INDEX
    Explanations

    This neuron detects code‐level annotations or decorators (e.g. “@Annotation” or “[Attribute]”) in source files.

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

    programming annotations and classes

    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
     that
    -1.38
     Método
    -1.12
    fordshire
    -1.09
     informacija
    -1.09
     bakso
    -1.08
    meisters
    -1.05
    haired
    -1.05
    hems
    -1.03
    breviations
    -1.01
    ıldı
    -1.01
    POSITIVE LOGITS
    inephrine
    1.00
     located
    0.99
     lâng
    0.94
    としている
    0.93
     ге
    0.93
    带宽
    0.91
    PARATUS
    0.90
     них
    0.89
    围绕
    0.88
     срав
    0.88
    Activations Density 0.001%

    No Known Activations