© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 80692
    Prev
    Next
    INDEX
    Explanations

    proper names with titles

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

    The neuron fires strongly on non-English word fragments—e.g. Gaelic place names, archaic “ye/erth/wyndes” Bible language, or Esperanto locale terms—i.e. foreign or unusual vocabulary chunks.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -3.84
     when
    -2.59
     after
    -2.47
     before
    -2.39
     unrelenting
    -2.27
     blatantly
    -2.25
     exquisitely
    -2.23
     supremely
    -2.22
     meticulous
    -2.20
     or
    -2.19
    POSITIVE LOGITS
     amazingly
    2.63
     unbelievably
    2.61
     REALLY
    2.47
     broader
    2.33
     remarkably
    2.33
     VERY
    2.25
     ridiculously
    2.23
     kinda
    2.22
    generally
    2.22
    descri
    2.20
    Activations Density 0.016%

    No Known Activations