© 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. 68748
    Prev
    Next
    INDEX
    Explanations

    James ButlerorLow back pain

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

    This neuron fires on tokens in non-Latin scripts—e.g. Devanagari or Cyrillic characters.

    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
      
    -3.36
    u
    -3.31
    x
    -3.25
    at
    -3.22
    "
    -3.20
    <i>
    -2.97
    <em>
    -2.86
    [
    -2.83
    S
    -2.81
    </
    -2.75
    POSITIVE LOGITS
    幃
    2.83
    猡
    2.70
    郿
    2.63
    咘
    2.55
    哢
    2.47
    棪
    2.45
    峩
    2.44
    趼
    2.41
     celebrado
    2.39
    鰨
    2.39
    Activations Density 0.000%

    No Known Activations