© 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. 110639
    Prev
    Next
    INDEX
    Explanations

    DEFAULT keyword

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

    the word "DEFAULT" in code, especially in configuration settings and database schemas.

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

    The neuron fires on the uppercase token “DEFAULT” (especially in macro or constant definitions).

    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
     But
    -3.08
     If
    -2.77
     Даже
    -2.28
    ם
    -2.16
     Если
    -2.09
    嶄
    -2.09
     Practically
    -2.08
    section
    -2.05
     crucible
    -2.03
     The
    -2.02
    POSITIVE LOGITS
    橚
    3.39
    ᯾
    3.39
    The
    2.91
    鹩
    2.80
    蟥
    2.73
    the
    2.66
    “”
    2.52
    栊
    2.52
    乄
    2.52
    са
    2.48
    Activations Density 0.003%

    No Known Activations