© 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. 22766
    Prev
    Next
    INDEX
    Explanations

    multi or multiple

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

    This neuron detects occurrences of the substring “multi” (as in multiline, multi-arch, multi-select, 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
    {
    -1.77
     Then
    -1.72
     yaklaşık
    -1.55
     next
    -1.52
    ↵
    -1.51
    ğinde
    -1.45
     Ergän
    -1.44
    dersfield
    -1.43
    soa
    -1.41
     I
    -1.38
    POSITIVE LOGITS
    鉨
    1.67
     motivadoras
    1.67
    鯓
    1.61
    笮
    1.59
     memperhatikan
    1.59
     botines
    1.58
     études
    1.58
     housse
    1.58
    不一样
    1.57
    デメリット
    1.57
    Activations Density 0.041%

    No Known Activations