© 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. 75548
    Prev
    Next
    INDEX
    Explanations

    Card and Row UI elements

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

    The neuron fires on mentions of Flutter UI widget class names (e.g. “ReorderableListView,” “TextField,” 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
    Serenity
    -0.80
     spru
    -0.77
    Roadmap
    -0.76
    Gobierno
    -0.76
    textcolor
    -0.75
     Flughafen
    -0.75
    Gek
    -0.75
     aggregating
    -0.73
    Poverty
    -0.72
    PageData
    -0.72
    POSITIVE LOGITS
    build
    1.15
    Card
    1.09
     build
    1.09
     card
    1.02
     Card
    1.00
    Row
    0.97
    カード
    0.94
    Padding
    0.89
     Row
    0.86
     header
    0.85
    Activations Density 0.002%

    No Known Activations