© 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. 90566
    Prev
    Next
    INDEX
    Explanations

    android ui drawables

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

    The neuron is strongly activated by Android XML namespace declarations and attributes (anything prefixed with “android:” in resource selector files).

    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
     Inclusion
    -1.22
    Inclusion
    -1.15
    inclusion
    -1.06
     inclusion
    -0.99
     inclusión
    -0.93
    Inclusive
    -0.92
    inclusive
    -0.91
     inclusive
    -0.88
     Inclusive
    -0.82
    quiagem
    -0.78
    POSITIVE LOGITS
     drawable
    1.41
    drawable
    1.40
    Drawable
    1.38
     Drawable
    1.05
     background
    1.02
     selector
    1.00
    Tint
    0.92
    getDrawable
    0.92
    selector
    0.91
     compound
    0.91
    Activations Density 0.038%

    No Known Activations