© 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. 75640
    Prev
    Next
    INDEX
    Explanations

    UIImageViewaddSubview

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

    This neuron detects mentions of UIKit view-related API symbols (e.g. UIView/UIImageView classes and methods like addSubview, insertSubview, UIScrollView, UITableView).

    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
     be
    -2.97
    l
    -2.64
    as
    -2.56
    end
    -2.33
    at
    -2.28
    B
    -2.28
     allow
    -2.27
    name
    -2.16
    ри
    -2.09
    re
    -2.06
    POSITIVE LOGITS
    蘩
    2.50
    驁
    2.25
    屨
    2.22
    鉏
    2.22
     célèbre
    2.20
    囖
    2.20
    ⸥
    2.17
    
    2.13
    瘓
    2.13
    什么的
    2.11
    Activations Density 0.001%

    No Known Activations