© 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. 83921
    Prev
    Next
    INDEX
    Explanations

    never followed by a verb

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

    This neuron specifically activates on the frequency adverbs “ever” and “never.”

    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
    geſ
    -2.88
    俛
    -2.88
     представители
    -2.78
    餮
    -2.77
    Ｙ
    -2.73
    ܞ
    -2.69
    茈
    -2.66
    歘
    -2.64
    䜣
    -2.64
    淙
    -2.61
    POSITIVE LOGITS
    If
    3.33
    It
    3.03
     After
    2.78
     проєкту
    2.69
     Originally
    2.67
     После
    2.59
     Everything
    2.53
    However
    2.48
    ization
    2.45
    what
    2.45
    Activations Density 0.022%

    No Known Activations