© 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. 13976
    Prev
    Next
    INDEX
    Explanations

    foreign names and titles

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

    The neuron activates on proper names—especially personal or place names rendered with non-English characters or in non-Latin scripts.

    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
     our
    -2.53
     who
    -1.80
     your
    -1.75
     Arzneimit
    -1.68
     my
    -1.66
    shadowRadius
    -1.60
    liptical
    -1.58
    viaf
    -1.57
     the
    -1.56
    ınıza
    -1.55
    POSITIVE LOGITS
     wichtigsten
    1.52
    There
    1.52
    توضیحات
    1.49
    Zitat
    1.40
    YourGuide
    1.39
    معرفی
    1.39
     suaves
    1.38
    資料來源
    1.37
     作り方
    1.37
    Some
    1.35
    Activations Density 0.443%

    No Known Activations