© 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. 11764
    Prev
    Next
    INDEX
    Explanations

    gccgo

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

    references to the GCC compiler or compilation tools in technical code and documentation.

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

    The neuron fires on multi‐letter uppercase acronyms and proper‐name abbreviations (e.g. UNHCR, GCC, Reuters).

    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
    
    -3.66
     trám
    -3.47
    ৢ
    -3.47
    ⁛
    -3.47
    튿
    -3.20
     dán
    -3.19
    댔
    -3.03
     différents
    -2.98
    ౮
    -2.95
    衒
    -2.95
    POSITIVE LOGITS
    ’
    4.97
    s
    3.66
    t
    3.56
    h
    3.56
    In
    3.30
    te
    3.25
    .
    3.23
    Even
    3.17
    $
    3.16
    ’，
    3.03
    Activations Density 0.004%

    No Known Activations