© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39728
    Prev
    Next
    INDEX
    Explanations

    keywords or identifiers

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

    The neuron detects programming-specific identifiers and keywords (e.g. include, require, Transform, load, double, etc.) in code snippets.

    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
     Ağustos
    -1.04
     žel
    -0.97
     confé
    -0.94
    drawRect
    -0.94
    ceous
    -0.91
    efd
    -0.91
     καν
    -0.91
    initro
    -0.87
     trabaj
    -0.87
     أجل
    -0.86
    POSITIVE LOGITS
    0.86
    红的
    0.80
        
    0.79
    ير
    0.78
     QtWidgets
    0.77
     schlug
    0.76
    ove
    0.75
    such
    0.73
     främ
    0.73
    стов
    0.72
    Activations Density 0.193%

    No Known Activations