© 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. 34-GEMMASCOPE-RES-131K
    7. 48828
    Prev
    Next
    INDEX
    Explanations

    android app automation using findElement

    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_34/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
    鼠标
    -0.83
     באתר
    -0.81
    モリ
    -0.78
     Lily
    -0.75
    浏览器
    -0.74
    gypti
    -0.73
    響
    -0.71
     ál
    -0.70
    食べたい
    -0.69
     biggest
    -0.68
    POSITIVE LOGITS
     swipe
    1.08
     Swipe
    0.99
     Android
    0.93
    Swipe
    0.92
     Ui
    0.90
    swipe
    0.89
     android
    0.88
     app
    0.85
    android
    0.84
    droid
    0.84
    Activations Density 0.014%

    No Known Activations