© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63771
    Prev
    Next
    INDEX
    Explanations

    android layout xml

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

    The neuron activates on numeric tokens (any standalone numbers or digits) in the document.

    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
    rgba
    -0.82
    friendly
    -0.74
     Chất
    -0.73
    Ảnh
    -0.72
     Levi
    -0.72
     Fur
    -0.71
    eschön
    -0.70
    lucent
    -0.69
     jobb
    -0.69
     père
    -0.68
    POSITIVE LOGITS
     layout
    1.59
     layouts
    1.57
     getLayout
    1.20
    layout
    1.17
    布局
    1.16
     LAYOUT
    1.16
     Layout
    1.09
    Layout
    1.05
    setContentView
    1.00
    Layouts
    0.98
    Activations Density 0.004%

    No Known Activations