© 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. 34-GEMMASCOPE-RES-131K
    7. 118350
    Prev
    Next
    INDEX
    Explanations

    widget

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

    This neuron flags Java code import statements from the Android widget package (i.e. lines importing android.widget.*).

    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
     what
    -1.03
     wären
    -0.98
     should
    -0.91
     which
    -0.90
     νό
    -0.89
     would
    -0.82
     even
    -0.82
     They
    -0.82
     all
    -0.77
    فرد
    -0.77
    POSITIVE LOGITS
    remote
    1.15
    Remote
    1.03
     området
    1.02
    widget
    1.01
    ств
    0.95
    Toast
    0.94
    popup
    0.91
     Spisak
    0.91
     توضیح
    0.90
     REMOTE
    0.89
    Activations Density 0.002%

    No Known Activations