© 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. 10-GEMMASCOPE-RES-131K
    7. 66506
    Prev
    Next
    INDEX
    Explanations

    conditional expressions and `in`

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

    This neuron fires on the “==” comparison operator (and related equality‐test syntax) in shell-style conditional expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     unrelenting
    -1.95
     had
    -1.70
    '
    -1.66
     because
    -1.56
     for
    -1.54
     ostensibly
    -1.53
     as
    -1.48
     multifaceted
    -1.48
     مختلفة
    -1.47
     by
    -1.43
    POSITIVE LOGITS
     exceptionally
    1.95
     jednej
    1.92
     habiendo
    1.73
    𝓙
    1.71
     unbelievably
    1.70
     teniendo
    1.66
     vastly
    1.63
    灕
    1.63
     jednego
    1.62
     lauded
    1.62
    Activations Density 0.010%

    No Known Activations