© 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. 87289
    Prev
    Next
    INDEX
    Explanations

    UI alerts and dialogs

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

    This neuron detects references to Android AlertDialog (and its Builder) classes in import statements or instantiation code.

    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
    ाहरण
    -1.01
    amanca
    -0.82
    blog
    -0.80
    汇
    -0.79
    gdala
    -0.78
     poo
    -0.77
     ur
    -0.77
    ntesis
    -0.77
     않는
    -0.75
    inson
    -0.75
    POSITIVE LOGITS
    AlertDialog
    0.92
     Sill
    0.85
    Minister
    0.84
    WINDOW
    0.82
    CONT
    0.81
    стях
    0.81
    mPaint
    0.80
     EXISTS
    0.80
     Barbier
    0.80
    QUET
    0.79
    Activations Density 0.004%

    No Known Activations