© 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. 83927
    Prev
    Next
    INDEX
    Explanations

    demonstrative and relative pronouns

    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
    Not in Any Lists

    No Comments

    Negative Logits
     hodně
    -1.42
     rápid
    -1.37
    だったが
    -1.34
     uscire
    -1.32
     trovano
    -1.32
    maty
    -1.31
    帮我
    -1.30
     Vereinbarung
    -1.30
     gegangen
    -1.30
     тебя
    -1.30
    POSITIVE LOGITS
     that
    2.33
     who
    2.06
     الذي
    1.84
     που
    1.73
     where
    1.59
     whose
    1.58
     those
    1.50
    at
    1.48
    m
    1.46
     which
    1.45
    Activations Density 0.021%

    No Known Activations