© 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. 34-GEMMASCOPE-RES-131K
    7. 7779
    Prev
    Next
    INDEX
    Explanations

    code editor context

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

    The neuron fires on mentions of text‐editor or IDE UI components and settings (e.g. “editor,” “vim,” “ipython-input,” preference keys for editors).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     khắp
    -0.81
    ｼ
    -0.78
    nezeu
    -0.78
     افزار
    -0.74
     kepolisian
    -0.71
    ması
    -0.70
     accompanied
    -0.69
     documented
    -0.69
     いる
    -0.68
     建設
    -0.68
    POSITIVE LOGITS
    fold
    1.07
    FOLD
    1.02
    Fold
    0.99
     editors
    0.90
    ⎔
    0.88
     editor
    0.88
    editor
    0.88
    шивания
    0.86
    itage
    0.86
     editing
    0.86
    Activations Density 0.001%

    No Known Activations