© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58100
    Prev
    Next
    INDEX
    Explanations

    special characters and diacritics

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

    This neuron activates on characters with diacritics or other non-ASCII symbols (e.g. ü, ä, ö, É, etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     there
    -1.71
     an
    -1.59
     mempel
    -1.57
     besucht
    -1.55
     estómago
    -1.52
     immensely
    -1.52
    ampiyon
    -1.52
     škoda
    -1.48
     zdra
    -1.43
     zelen
    -1.42
    POSITIVE LOGITS
    .
    2.03
    﨑
    1.59
    {
    1.59
     اهم
    1.55
    峮
    1.55
     cyclisme
    1.53
    媄
    1.53
    ION
    1.49
    GEN
    1.48
    Δ
    1.48
    Activations Density 0.016%

    No Known Activations