© 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. 99224
    Prev
    Next
    INDEX
    Explanations

    runtime proto schemas

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

    The neuron fires on occurrences of the identifier “runtime” (in any capitalization) in 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
     more
    -0.93
     steadily
    -0.88
     enticing
    -0.82
     it
    -0.82
     Oth
    -0.79
     best
    -0.79
     dismay
    -0.79
     unrelenting
    -0.77
     literally
    -0.77
     desperately
    -0.77
    POSITIVE LOGITS
    TagHelpers
    1.09
    į
    0.95
     버튼
    0.94
    did
    0.90
    不夠
    0.90
    might
    0.88
     gâ
    0.87
    Bjs
    0.87
    ért
    0.86
    mitted
    0.85
    Activations Density 0.001%

    No Known Activations