© 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. 91536
    Prev
    Next
    INDEX
    Explanations

    BorderLayout

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

    The neuron is triggered by numeric literals (stand‐alone numbers) in code or text snippets.

    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
    ność
    -0.90
    ći
    -0.84
    кновен
    -0.84
     drying
    -0.81
     iyon
    -0.79
    AsUp
    -0.78
     計
    -0.77
     Janata
    -0.76
    шма
    -0.76
     dried
    -0.75
    POSITIVE LOGITS
     BorderLayout
    0.82
    ⌠
    0.73
    sixth
    0.71
    BorderLayout
    0.71
    实时
    0.69
     clockwise
    0.68
    下一步
    0.68
     tertentu
    0.68
     loos
    0.67
     coverings
    0.66
    Activations Density 0.001%

    No Known Activations