© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27410
    Prev
    Next
    INDEX
    Explanations

    MVC routes and controllers

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

    The neuron fires on code tokens that name major components or types—e.g. controllers, views, classes or modules—typically in PascalCase.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     FormGroup
    -1.09
     laku
    -1.09
     like
    -1.04
     kutu
    -1.01
    ಳ
    -0.99
     miliar
    -0.99
    onnaise
    -0.96
     galeri
    -0.95
     juta
    -0.94
     triko
    -0.94
    POSITIVE LOGITS
    effetto
    0.99
     Puts
    0.94
     we
    0.93
    Belgique
    0.93
    putting
    0.93
     áng
    0.93
     vérit
    0.91
     pearly
    0.87
    快点
    0.87
     Sigue
    0.86
    Activations Density 0.003%

    No Known Activations