© 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. 127753
    Prev
    Next
    INDEX
    Explanations

    but what

    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
     malgré
    -0.83
     weder
    -0.82
    baran
    -0.79
    gebung
    -0.77
     שה
    -0.77
     любом
    -0.77
    мента
    -0.74
     soit
    -0.73
     ancien
    -0.72
     activité
    -0.72
    POSITIVE LOGITS
     but
    1.96
     what
    1.24
     tetapi
    1.21
    But
    1.14
    However
    1.13
     rarer
    1.13
    但
    1.10
     But
    1.09
     However
    1.06
     however
    1.02
    Activations Density 0.167%

    No Known Activations