© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25855
    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
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -1.27
     all
    -1.25
     would
    -1.10
     stycznia
    -1.09
     before
    -1.09
     their
    -1.09
     Desember
    -1.04
     from
    -1.02
     września
    -1.01
     Zugriff
    -1.01
    POSITIVE LOGITS
     mães
    1.38
     traducciones
    1.32
     trám
    1.29
    ݮ
    1.23
     taky
    1.23
     tyto
    1.21
     actuales
    1.21
    ܆
    1.20
     preferências
    1.19
     ܕ
    1.17
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.