© 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. 10-GEMMASCOPE-RES-131K
    7. 12732
    Prev
    Next
    INDEX
    Explanations

    programming data structures

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

    The neuron fires on generic collection declarations/instantiations (e.g. occurrences of “List<…>” and “new List<…>”).

    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
     first
    -2.17
     most
    -1.95
     only
    -1.88
     because
    -1.80
     and
    -1.70
     there
    -1.68
     after
    -1.60
     \
    -1.55
     not
    -1.54
     one
    -1.54
    POSITIVE LOGITS
     of
    3.47
     mépris
    1.85
     véhic
    1.75
     soulign
    1.65
     récol
    1.58
     visse
    1.55
     rafraî
    1.52
    閖
    1.49
     perpé
    1.49
    神
    1.48
    Activations Density 0.006%

    No Known Activations