© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8561
    Prev
    Next
    INDEX
    Explanations

    year-round

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

    The neuron fires whenever it sees the phrase “year-round” (i.e. “year-” followed by “round”), marking all-year or continuous duration mentions.

    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
    หรือ
    -2.05
    ჻
    -1.98
    欺负
    -1.88
    觊
    -1.80
    あるいは
    -1.73
    もしくは
    -1.73
    
    -1.67
    èvent
    -1.66
     proverbial
    -1.63
    盉
    -1.62
    POSITIVE LOGITS
    ؛
    1.90
    '
    1.81
     estekak
    1.79
    (
    1.78
    릭터
    1.77
    ︰
    1.70
     They
    1.66
    一个
    1.65
    ；
    1.63
     serisi
    1.62
    Activations Density 0.003%

    No Known Activations