© 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. 22-GEMMASCOPE-RES-131K
    7. 130584
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on import statements referring to Android “widget” packages (e.g. android.support.v7.widget or androidx.recyclerview.widget).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    android ui components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     to
    -1.93
     
    -1.23
     a
    -1.23
    '
    -1.20
     Configuración
    -1.09
     Descripción
    -1.07
    es
    -1.07
     for
    -1.06
     return
    -1.05
     represent
    -1.05
    POSITIVE LOGITS
    あなたの
    1.35
    あなたは
    1.33
    مدیر
    1.30
    みなさん
    1.27
    お世話
    1.27
    灃
    1.24
    strando
    1.23
    もうすぐ
    1.23
    Literat
    1.20
    گروه
    1.20
    Activations Density 0.001%

    No Known Activations