© 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. 101240
    Prev
    Next
    INDEX
    Explanations

    we/you followed by verb or possession

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     andere
    -1.52
     seront
    -1.41
     nimmer
    -1.36
    possibly
    -1.34
     autre
    -1.34
     Itali
    -1.34
    sibly
    -1.31
     unie
    -1.31
    螓
    -1.30
     externe
    -1.30
    POSITIVE LOGITS
     with
    1.91
     people
    1.80
     not
    1.74
     when
    1.66
     their
    1.60
     because
    1.57
     those
    1.51
     from
    1.48
     Because
    1.45
     it
    1.41
    Activations Density 0.030%

    No Known Activations