© 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. 130562
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on code or text referring to modal/dialog/alert boxes (e.g. AlertDialog, UIAlertController, modal, confirm/pop-up).

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

    dialog box

    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
    parently
    -1.19
     saus
    -1.18
     práticas
    -1.13
     siena
    -1.10
    たまに
    -1.09
    啐
    -1.08
    grees
    -1.08
    ided
    -1.05
     スパ
    -1.05
     kei
    -1.05
    POSITIVE LOGITS
     Noruega
    1.20
    aspectj
    1.16
     empresas
    1.09
     clases
    1.08
     eventos
    1.07
     ondas
    1.06
     tæn
    1.06
     componentes
    1.05
    เปิด
    1.05
    Σε
    1.05
    Activations Density 0.027%

    No Known Activations