© 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. 54265
    Prev
    Next
    INDEX
    Explanations

    message boxes and alerts

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

    The neuron fires on code tokens naming or invoking alert dialogs (e.g. “UIAlert”, “alert”), i.e. it detects references to alert‐related UI classes and methods.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    '
    -1.03
    h
    -1.02
    j
    -0.99
    sp
    -0.98
    per
    -0.96
    g
    -0.96
    al
    -0.96
    v
    -0.94
    ai
    -0.94
    íritu
    -0.93
    POSITIVE LOGITS
    brainly
    1.30
     avenir
    1.22
    عرض
    1.21
     variantes
    1.16
     reservas
    1.16
    UIAlert
    1.15
     desmotiv
    1.14
     biela
    1.14
     pincel
    1.14
    marry
    1.13
    Activations Density 0.009%

    No Known Activations