© 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. 108279
    Prev
    Next
    INDEX
    Explanations

    android layout attributes

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

    The neuron is looking for numeric literals (digits or numbers) in the XML/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_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
    гры
    -0.90
    سجيل
    -0.86
    ēs
    -0.85
     Magnolia
    -0.76
    oiden
    -0.75
    titleMargin
    -0.75
    넨
    -0.75
    anen
    -0.75
     Samar
    -0.75
     Loren
    -0.74
    POSITIVE LOGITS
     android
    0.79
     src
    0.76
    src
    0.75
    Preserve
    0.74
     Preserve
    0.73
    arım
    0.72
     maintien
    0.71
    android
    0.71
     preserve
    0.71
     Го
    0.70
    Activations Density 0.006%

    No Known Activations