© 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. 104603
    Prev
    Next
    INDEX
    Explanations

    UI elements and code structures

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

    Android programming code, particularly UI-related class names and methods like TextView, Layout, Dialog, and widget components.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects mentions of Android UI widget and view class names (e.g. DatePicker, EditText, TextView, ImageView).

    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
     '../../../../
    -1.21
     those
    -1.21
     Bø
    -1.20
     われ
    -1.17
    ubehör
    -1.16
    ⬡
    -1.16
    اية
    -1.15
    諳
    -1.15
    **************
    -1.13
    hibition
    -1.13
    POSITIVE LOGITS
    ercicio
    1.33
     قبل
    1.14
     =
    1.14
     will
    1.12
    寨
    1.08
    lück
    1.06
     dagger
    1.05
     Freude
    1.05
     sammen
    1.04
     öğren
    1.04
    Activations Density 0.256%

    No Known Activations