© 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. 32571
    Prev
    Next
    INDEX
    Explanations

    compound noun formation

    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
     dilapidated
    -1.64
     shimmering
    -1.51
     まる
    -1.48
     magnific
    -1.48
     immense
    -1.48
     unbelievably
    -1.48
     hugely
    -1.46
     quintessential
    -1.45
     is
    -1.43
     goofy
    -1.41
    POSITIVE LOGITS
     and
    2.05
     this
    1.64
     during
    1.43
     any
    1.41
     after
    1.38
     bicicletas
    1.37
     sehr
    1.35
    dö
    1.34
    ėtų
    1.34
     誌
    1.33
    Activations Density 0.088%

    No Known Activations