© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82667
    Prev
    Next
    INDEX
    Explanations

    UI control names followed by numbers

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

    This neuron fires on code tokens that are .NET/WinForms API identifiers—especially class or method names like FolderBrowserDialog, ShowDialog, ScriptManager, WebBrowser, etc.

    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
     eighty
    -1.08
     forty
    -1.05
     ninety
    -1.02
     seventy
    -1.02
     thirty
    -1.02
     eighteen
    -0.99
     Thirteen
    -0.98
     Eighteen
    -0.96
     sixty
    -0.96
     XXXIV
    -0.95
    POSITIVE LOGITS
    1
    1.38
     ۱
    1.31
    TextBoxColumn
    1.09
    1
    1.07
    ۱
    1.03
     Свя
    0.84
     ONE
    0.81
    Архівовано
    0.79
     الف
    0.79
    iries
    0.77
    Activations Density 0.032%

    No Known Activations