© 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. 36256
    Prev
    Next
    INDEX
    Explanations

    SwiftUI view elements

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

    The neuron is keyed to occurrences of the SwiftUI framework (e.g. “SwiftUI” imports, links, headings, etc.).

    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
    쟈
    -1.15
     České
    -1.15
    際には
    -1.09
    
    -1.09
    際は
    -1.09
     転
    -1.09
     mangoes
    -1.07
     dinoss
    -1.07
    iewicz
    -1.05
     CONSE
    -1.05
    POSITIVE LOGITS
     realmente
    1.38
    其实
    1.34
    「
    1.27
    로
    1.23
     usando
    1.20
     mostrar
    1.19
     только
    1.17
    使用
    1.15
     actriz
    1.15
    giat
    1.14
    Activations Density 0.002%

    No Known Activations