© 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. 38517
    Prev
    Next
    INDEX
    Explanations

    ending punctuation followed by words

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

    This neuron detects discourse markers that introduce an answer (e.g. “Yes,” “No,” “Well,” “Absolutely,” 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
     dessutom
    -1.62
    However
    -1.41
     vegano
    -1.33
     termino
    -1.33
     roligt
    -1.31
    Other
    -1.30
     anledning
    -1.27
     выполнять
    -1.23
     myndig
    -1.23
    heids
    -1.23
    POSITIVE LOGITS
     they
    1.86
     and
    1.38
     habiendo
    1.32
     هذه
    1.26
     człon
    1.20
     Entfer
    1.19
     incluyendo
    1.18
     эту
    1.18
     ∼
    1.17
    まったく
    1.15
    Activations Density 0.006%

    No Known Activations