© 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. 22-GEMMASCOPE-RES-131K
    7. 36454
    Prev
    Next
    INDEX
    Explanations

    programming library names

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

    The neuron fires on mentions of programming libraries or module names (e.g., “QtGui”, “numpy”, “nn”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     through
    -1.29
     sehr
    -1.17
    !!!!!
    -1.11
     áreas
    -1.11
     mín
    -1.09
    ochond
    -1.06
     and
    -1.05
     took
    -1.04
    🍕
    -1.03
     dazzling
    -1.02
    POSITIVE LOGITS
     quintessential
    1.44
     ridiculously
    1.41
     gigantic
    1.40
    without
    1.38
     dreadful
    1.37
     remarkably
    1.34
     exceedingly
    1.31
     magnific
    1.29
    thus
    1.27
     tremendous
    1.25
    Activations Density 0.009%

    No Known Activations