© 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. 83633
    Prev
    Next
    INDEX
    Explanations

    utterly, utmost, outermost

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

    The neuron activates on the intensifier “utter/utterly” (and related “utmost”)—strong adverbs that convey extreme degree.

    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
    originally
    -2.48
    댔
    -2.41
    GEBUR
    -2.38
     刺繍
    -2.34
    сторінку
    -2.31
    indicate
    -2.28
     is
    -2.20
    臜
    -2.20
     juſt
    -2.19
    箧
    -2.17
    POSITIVE LOGITS
    Only
    2.89
    1
    2.86
     When
    2.78
     There
    2.59
    there
    2.53
     Only
    2.47
    Although
    2.47
     That
    2.47
    when
    2.45
    та
    2.41
    Activations Density 0.001%

    No Known Activations