© 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. 10-GEMMASCOPE-RES-131K
    7. 11095
    Prev
    Next
    INDEX
    Explanations

    code punctuation and symbols

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

    UI widget and view component declarations in code (particularly TableView, ComboBox, and similar GUI elements).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is specialized in spotting mentions of UI widget components or their imports (e.g. ListView, DatePicker, ToggleButtonGroup, QComboBox).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     when
    -1.75
     from
    -1.74
     because
    -1.58
     Perhaps
    -1.48
     —
    -1.43
    but
    -1.38
     but
    -1.37
     když
    -1.36
     to
    -1.34
    when
    -1.32
    POSITIVE LOGITS
    چرخ
    1.43
    eſt
    1.41
     hjälpa
    1.38
     choix
    1.36
    مرد
    1.35
     dekol
    1.30
     atento
    1.30
     máte
    1.28
     réduite
    1.28
     rapidement
    1.27
    Activations Density 0.076%

    No Known Activations