© 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. 98350
    Prev
    Next
    INDEX
    Explanations

    database exports and dumps

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

    The neuron fires on command‐line or code‐style tokens—program names, flags, file paths, redirects, and other shell/SQL command 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_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
     Nail
    -0.81
     ingreso
    -0.79
    даря
    -0.78
     okul
    -0.77
     Easter
    -0.76
     nail
    -0.75
    Nail
    -0.73
     Coat
    -0.73
    setCellValue
    -0.72
     infant
    -0.71
    POSITIVE LOGITS
     export
    2.02
     exported
    1.87
     exporting
    1.86
    Export
    1.80
     EXPORT
    1.79
    export
    1.78
     Export
    1.77
     dump
    1.72
    dump
    1.61
     backup
    1.58
    Activations Density 0.091%

    No Known Activations