© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40367
    Prev
    Next
    INDEX
    Explanations

    UIView subclass

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

    The neuron is triggered by occurrences of the literal token “UIView” in 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_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
    c
    -3.39
    ’
    -3.08
    ↵↵
    -2.94
    ).
    -2.91
    d
    -2.89
    b
    -2.88
    w
    -2.86
    x
    -2.80
    s
    -2.75
    n
    -2.73
    POSITIVE LOGITS
     selben
    2.94
     Hinblick
    2.75
    廨
    2.73
     burbu
    2.72
    堙
    2.55
    蓥
    2.53
    彞
    2.45
    鯷
    2.42
     sintomas
    2.38
    
    2.36
    Activations Density 0.003%

    No Known Activations