© 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. 15767
    Prev
    Next
    INDEX
    Explanations

    coumaric acid

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

    names or technical terms ending with "hler" or "ic" suffixes, particularly in scientific or programming contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    The neuron strongly activates on tokens containing the substring “hler” (e.g. German‐style names ending in “hler”).

    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
    ↵
    -4.97
    i
    -2.95
    \
    -2.77
    d
    -2.70
    ’
    -2.70
    er
    -2.56
     {
    -2.55
    ↵↵
    -2.47
    “
    -2.41
    you
    -2.38
    POSITIVE LOGITS
    鞏
    2.50
     memutus
    2.48
    ܊
    2.45
    金钱
    2.42
    ではまた
    2.39
     Problemen
    2.38
    婬
    2.36
    ੬
    2.34
     інших
    2.33
    ふう
    2.33
    Activations Density 0.010%

    No Known Activations