© 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. 32693
    Prev
    Next
    INDEX
    Explanations

    Jupyter notebook questions

    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
     would
    -1.68
    \
    -1.51
     ;
    -1.42
     by
    -1.41
     other
    -1.36
     of
    -1.36
     ,
    -1.35
    '
    -1.30
     at
    -1.23
    S
    -1.23
    POSITIVE LOGITS
     accél
    1.33
     prostředí
    1.31
     négo
    1.28
    isies
    1.28
    regated
    1.27
    ridescent
    1.24
    bringt
    1.24
    mentación
    1.21
     réinitial
    1.20
    instellungen
    1.20
    Activations Density 0.031%

    No Known Activations