© 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. 16447
    Prev
    Next
    INDEX
    Explanations

    is followed by noun phrase description

    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
    Not in Any Lists

    No Comments

    Negative Logits
     while
    -2.17
     when
    -2.17
     that
    -2.00
     each
    -1.82
     cuando
    -1.59
     time
    -1.55
     their
    -1.52
     necessary
    -1.50
     simpler
    -1.49
     ample
    -1.48
    POSITIVE LOGITS
     currently
    1.97
     jaunes
    1.84
     a
    1.67
     also
    1.62
    currently
    1.45
     rivi
    1.41
     rusa
    1.39
    glad
    1.37
     maman
    1.36
     momente
    1.36
    Activations Density 0.054%

    No Known Activations