© 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. 111013
    Prev
    Next
    INDEX
    Explanations

    home and theme configuration

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

    The neuron is keyed to long runs of leading whitespace (i.e. indentation) in code/XML.

    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
    drawImage
    -0.85
     अला
    -0.79
    rance
    -0.78
     ottobre
    -0.77
     siste
    -0.75
    րա
    -0.75
    executeUpdate
    -0.73
    ريم
    -0.73
     zaczą
    -0.73
    Ɍ
    -0.72
    POSITIVE LOGITS
     home
    1.39
    home
    1.27
     debug
    1.23
     routes
    1.21
    debug
    1.20
     theme
    1.17
    routes
    1.08
     themes
    1.02
    dark
    1.02
    theme
    1.00
    Activations Density 0.003%

    No Known Activations