© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93100
    Prev
    Next
    INDEX
    Explanations

    special characters and international text

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

    The neuron activates on tokens containing non-ASCII or non-Latin characters (e.g. foreign-script letters or accented 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_22/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
     avec
    -2.75
     Some
    -2.53
     If
    -2.31
     inception
    -2.27
     WITH
    -2.16
     Mitarbeitern
    -2.08
    之事
    -2.08
     a
    -2.06
    芗
    -1.99
     excessively
    -1.95
    POSITIVE LOGITS
    0
    3.20
    >
    2.69
    eſ
    2.41
    ครื่อง
    2.31
    ?”
    2.30
    ዣ
    2.28
    鼋
    2.25
    ATURES
    2.22
     questa
    2.22
     iſt
    2.19
    Activations Density 0.002%

    No Known Activations