© 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. 83840
    Prev
    Next
    INDEX
    Explanations

    instead of or rather than

    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
     refroid
    -1.25
     już
    -1.13
    𝐌
    -1.12
     zaten
    -1.11
     résine
    -1.09
     récon
    -1.09
    arova
    -1.08
    áklad
    -1.08
     tphcm
    -1.06
    んで
    -1.05
    POSITIVE LOGITS
     instead
    2.47
     for
    1.89
     by
    1.59
     in
    1.57
    Instead
    1.56
    instead
    1.56
     because
    1.55
     rather
    1.55
     вместо
    1.48
     Instead
    1.43
    Activations Density 0.240%

    No Known Activations