© 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. 22-GEMMASCOPE-RES-131K
    7. 73902
    Prev
    Next
    INDEX
    Explanations

    conjunctions indicating consequence

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

    The neuron fires on formal technical transition words and conjunctive adverbs—e.g. “thus,” “next,” “subsequently,” “then”—that link clauses in patent‐style prose.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     årene
    -1.09
     meskipun
    -1.05
     spørsmål
    -1.04
     onsdag
    -1.03
     meski
    -0.97
     børn
    -0.95
     walaupun
    -0.94
     kropp
    -0.94
     kän
    -0.94
     Виктор
    -0.93
    POSITIVE LOGITS
     and
    0.97
     etc
    0.93
     tedes
    0.86
     werd
    0.85
     [
    0.85
     been
    0.84
     आगे
    0.84
     examine
    0.82
     so
    0.81
    deling
    0.81
    Activations Density 0.217%

    No Known Activations