© 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. 23518
    Prev
    Next
    INDEX
    Explanations

    content structure selectors

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

    This neuron flags mentions of “tab” (e.g. variable names, parameters, or events involving tabs) in 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_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
     TextView
    -0.86
     button
    -0.84
     JButton
    -0.82
    Serviço
    -0.82
    nologie
    -0.80
     JLabel
    -0.79
    boton
    -0.79
    BUTTON
    -0.79
     링크
    -0.79
     MenuItem
    -0.78
    POSITIVE LOGITS
     content
    2.70
    content
    2.30
    Content
    1.98
     main
    1.96
     container
    1.95
     body
    1.86
    CONTENT
    1.84
    内容
    1.78
     Content
    1.77
     CONTENT
    1.68
    Activations Density 0.155%

    No Known Activations