© 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. 10-GEMMASCOPE-RES-131K
    7. 41574
    Prev
    Next
    INDEX
    Explanations

    UIKit imports and usage

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

    The neuron fires on mentions of the “UIKit” framework (e.g. import or class declarations involving UIKit).

    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
    现在的
    -2.69
    鳢
    -2.66
    ейчас
    -2.66
    ➑
    -2.63
    橚
    -2.55
    鹮
    -2.52
     аккура
    -2.50
    蛱
    -2.48
    
    -2.47
    ㌘
    -2.45
    POSITIVE LOGITS
    的我
    2.72
    -
    2.55
    [
    2.50
    or
    2.47
    of
    2.44
    ,"
    2.17
     программы
    2.16
    -"
    2.13
    ...
    2.08
     â
    2.02
    Activations Density 0.001%

    No Known Activations