© 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. 22699
    Prev
    Next
    INDEX
    Explanations

    starts questions

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

    This neuron detects the presence of a question mark (i.e. identifies sentence-ending question punctuation).

    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
     or
    -1.63
     as
    -1.63
     our
    -1.57
     where
    -1.56
     by
    -1.55
    Like
    -1.39
     {
    -1.36
    Since
    -1.31
     extenso
    -1.27
    Only
    -1.26
    POSITIVE LOGITS
     naudoti
    1.77
    真好
    1.64
    ASONS
    1.62
    גו
    1.55
     anoche
    1.51
     trabajó
    1.48
     beinahe
    1.46
    siguiente
    1.42
     préstamo
    1.41
    它的
    1.40
    Activations Density 0.183%

    No Known Activations