© 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. 25010
    Prev
    Next
    INDEX
    Explanations

    negative contractions ending in n't

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    e
    -2.80
    er
    -2.34
    y
    -2.23
    o
    -2.19
    u
    -2.13
    a
    -2.13
    umbria
    -2.09
    fourths
    -2.08
    かは
    -2.08
     to
    -2.08
    POSITIVE LOGITS
    '
    2.06
    無論
    1.98
     schlä
    1.91
    kemeja
    1.77
    dür
    1.73
    是
    1.69
    ：　
    1.67
    -
    1.67
     If
    1.66
    了一
    1.66
    Activations Density 0.038%

    No Known Activations