© 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. 32792
    Prev
    Next
    INDEX
    Explanations

    expresses enjoyment

    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
     for
    -1.73
     some
    -1.70
     on
    -1.66
     a
    -1.65
     with
    -1.58
     an
    -1.50
     after
    -1.45
     one
    -1.43
     also
    -1.39
     before
    -1.37
    POSITIVE LOGITS
    튿
    1.28
     alho
    1.27
    seiten
    1.27
     legendar
    1.25
    mense
    1.25
     素描
    1.25
     ſie
    1.24
    arbeiten
    1.23
    瞟
    1.23
    卝
    1.21
    Activations Density 0.018%

    No Known Activations