© 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. 124741
    Prev
    Next
    INDEX
    Explanations

    language greetings and closings

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

    The neuron fires strongly on runs of East Asian characters (e.g. Japanese or Chinese text).

    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
    喾
    -2.19
    ᭝
    -2.00
    鴣
    -2.00
    estões
    -1.98
    逦
    -1.93
    CGRectMake
    -1.87
    鈰
    -1.87
    OUS
    -1.84
    蟳
    -1.84
    čka
    -1.83
    POSITIVE LOGITS
     they
    2.73
    "
    1.95
     haupts
    1.94
     that
    1.88
     größ
    1.81
    >
    1.80
     ältere
    1.79
    你
    1.79
    k
    1.77
    大的
    1.71
    Activations Density 0.000%

    No Known Activations