© 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. 11826
    Prev
    Next
    INDEX
    Explanations

    foreign languages and technical terms

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

    The neuron fires strongly on foreign‐language words and proper names (especially non-common English or accented/Unicode tokens).

    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
    ”,
    -2.77
    姈
    -2.67
    ꜆
    -2.58
     *.
    -2.50
     senza
    -2.38
    '
    -2.38
    ↵
    -2.33
     cinq
    -2.28
     huit
    -2.25
    𓆉
    -2.23
    POSITIVE LOGITS
    cayaan
    2.53
    荩
    2.44
    ୈ
    2.41
    多谢
    2.39
    ी
    2.38
    י
    2.36
    ي
    2.28
     gustaMe
    2.25
    可以说
    2.22
    堙
    2.22
    Activations Density 0.090%

    No Known Activations