© 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. 101774
    Prev
    Next
    INDEX
    Explanations

    enum definitions

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

    the opening curly brace of enum declarations in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is specialized to pick out numeric literals (integer or floating‐point constants) in source 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_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
     huge
    -2.06
     intensely
    -2.03
     eight
    -1.95
     innovative
    -1.93
     enormous
    -1.91
     two
    -1.84
     sehr
    -1.82
     ostensibly
    -1.80
     extraordinary
    -1.79
     three
    -1.77
    POSITIVE LOGITS
    颪
    2.25
    轳
    2.23
     REALLY
    2.19
     soooo
    2.19
     wacky
    2.02
     delightfully
    2.02
    睃
    1.98
    seems
    1.93
     goofy
    1.90
     ridiculously
    1.88
    Activations Density 0.012%

    No Known Activations