© 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. 44520
    Prev
    Next
    INDEX
    Explanations

    multilingual text beginnings

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

    The neuron flags tokens written in non-Latin scripts (e.g. Arabic, Hebrew, Chinese characters).

    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
     from
    -1.91
     with
    -1.84
     after
    -1.80
     although
    -1.67
     shows
    -1.65
    <blockquote>
    -1.65
    "
    -1.60
     on
    -1.59
     increase
    -1.57
     obwohl
    -1.55
    POSITIVE LOGITS
    鸶
    1.92
     superbe
    1.77
     墊
    1.71
    硨
    1.70
     siena
    1.70
    鰨
    1.68
    瓛
    1.68
     tâ
    1.68
     auffi
    1.67
     ché
    1.67
    Activations Density 0.002%

    No Known Activations