© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9392
    Prev
    Next
    INDEX
    Explanations

    closing punctuation and brackets

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

    The neuron strongly activates on mixed-case (Pascal/CamelCase) identifiers (especially method or function names) in source code.

    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
    xiii
    -0.85
     Ther
    -0.80
    phors
    -0.79
     Kim
    -0.79
     Milan
    -0.78
    Ther
    -0.77
    xii
    -0.77
     by
    -0.76
    footnotes
    -0.75
    xvii
    -0.75
    POSITIVE LOGITS
     erstellt
    0.88
     sababu
    0.87
    upassen
    0.86
     incontra
    0.85
    なかった
    0.84
    ̼
    0.84
    ͖
    0.83
     mittleren
    0.82
     pamoja
    0.82
     CODES
    0.82
    Activations Density 0.006%

    No Known Activations