© 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. 7577
    Prev
    Next
    INDEX
    Explanations

    Japanese name `寛理`

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

    The neuron activates on occurrences of the pinyin syllable “duan” (as in proper names or terms transliterated from Chinese).

    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
     Это
    -2.88
     Luckily
    -2.63
     また
    -2.53
    aults
    -2.47
     That
    -2.47
     Again
    -2.42
     But
    -2.39
     They
    -2.38
     We
    -2.36
    瀦
    -2.36
    POSITIVE LOGITS
    '
    2.48
    w
    2.44
    d
    2.44
    the
    2.38
    尤其是
    2.36
    am
    2.31
    IN
    2.30
    F
    2.25
    檍
    2.23
    時間は
    2.22
    Activations Density 0.005%

    No Known Activations