© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102900
    Prev
    Next
    INDEX
    Explanations

    multiple languages

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

    text in non-English languages, particularly Germanic and Slavic languages like German, Dutch, and Russian.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron flags tokens that are clearly non-English—i.e. foreign‐language words or characters (including accented letters and non-Latin script).

    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
     rése
    -1.86
    ⎔
    -1.80
     aussit
    -1.67
    РЫ
    -1.62
     dieu
    -1.62
     journaliste
    -1.59
     排骨
    -1.58
     {
    -1.58
    ܖ
    -1.51
     benzin
    -1.49
    POSITIVE LOGITS
     is
    1.70
     will
    1.69
    6
    1.68
     innych
    1.66
    3
    1.64
     other
    1.62
     otros
    1.61
     or
    1.58
    因为他
    1.56
    How
    1.55
    Activations Density 0.024%

    No Known Activations