© 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. 115996
    Prev
    Next
    INDEX
    Explanations

    code event handlers

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

    The neuron is spotting underscore characters in code identifiers (especially in C# method/event names).

    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
    WHY
    -0.86
     gruppen
    -0.84
     invitations
    -0.82
     Preguntas
    -0.81
    𝗨
    -0.79
     Configuración
    -0.78
    MenuGroup
    -0.78
     Varianten
    -0.75
     invitation
    -0.75
    izeit
    -0.75
    POSITIVE LOGITS
    に戻
    0.87
     Load
    0.85
    contextMenu
    0.82
    あま
    0.82
     находится
    0.82
     On
    0.81
     или
    0.81
    kében
    0.79
    ()
    0.79
     Enter
    0.79
    Activations Density 0.002%

    No Known Activations