© 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. 26248
    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
     =
    -1.00
     дали
    -0.96
     Vergine
    -0.96
    瞠
    -0.95
    ánicos
    -0.95
    D
    -0.93
    вня
    -0.93
    é
    -0.92
    охо
    -0.91
     <
    -0.91
    POSITIVE LOGITS
    Biblia
    1.18
     знал
    1.09
    عکس
    1.06
     voordelen
    1.03
    ają
    1.02
    Royaume
    1.02
    Ǟ
    1.00
    𝑍
    1.00
    Espace
    1.00
     leña
    1.00
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.