© 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. 22-GEMMASCOPE-RES-131K
    7. 16518
    Prev
    Next
    INDEX
    Explanations

    math and definitions

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

    The neuron strongly activates on the word “What,” i.e. it detects occurrences of the question-starting token “What.”

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     pelatih
    -1.06
     аромат
    -1.05
     дюй
    -0.98
    рно
    -0.98
    فایل
    -0.98
    の準備
    -0.97
     changed
    -0.97
     bruge
    -0.96
    März
    -0.96
     Тогда
    -0.96
    POSITIVE LOGITS
     etc
    1.23
     и
    1.20
     ($('#
    1.19
    derry
    1.15
    iferous
    1.15
     و
    1.13
    vereignty
    1.13
    sightly
    1.09
    bodied
    1.08
    vereign
    1.07
    Activations Density 0.000%

    No Known Activations