© 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. 16718
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     from
    -1.77
     at
    -1.65
     or
    -1.61
     their
    -1.56
     and
    -1.55
     on
    -1.48
     for
    -1.47
     With
    -1.41
     taken
    -1.36
    為に
    -1.35
    POSITIVE LOGITS
    بسم
    1.47
    currently
    1.37
     agres
    1.33
    ኵ
    1.32
    これも
    1.32
     didik
    1.31
    küche
    1.30
    particularly
    1.29
     Berikut
    1.29
    QUET
    1.28
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.