© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85807
    Prev
    Next
    INDEX
    Explanations

    AlertDialog, Kickstarter, JComboBox

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

    The neuron fires on mentions of the Android AlertDialog class (i.e. tokens like “AlertDialog” or “alertDialog”).

    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
    l
    -3.22
    不管是
    -2.67
     we
    -2.58
     "
    -2.52
    OS
    -2.50
    AR
    -2.47
    鯷
    -2.44
    AT
    -2.28
    ERS
    -2.28
    p
    -2.23
    POSITIVE LOGITS
     stappen
    2.59
    .
    2.48
     verschillen
    2.42
     ярко
    2.36
     onderdelen
    2.34
     reputación
    2.34
     and
    2.31
    ıları
    2.31
     gebruikt
    2.30
     activiteiten
    2.27
    Activations Density 0.002%

    No Known Activations