© 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. 34-GEMMASCOPE-RES-131K
    7. 106145
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by past was/had/would

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     is
    -2.00
     has
    -1.30
    Been
    -1.28
     are
    -1.23
     हैं
    -1.16
     foram
    -1.16
    美味しいです
    -1.13
    зывают
    -1.10
    Went
    -1.09
     می‌گوید
    -1.09
    POSITIVE LOGITS
     was
    3.44
     would
    2.34
     could
    2.27
     had
    2.27
     وكان
    1.95
     ήταν
    1.78
     habían
    1.77
     were
    1.76
     knew
    1.73
     وكانت
    1.73
    Activations Density 0.153%

    No Known Activations