© 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. 15072
    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
    </h3>
    -1.38
     гостиной
    -1.04
        
    -0.98
     начать
    -0.96
     truco
    -0.94
     Améli
    -0.93
     vì
    -0.91
    愎
    -0.91
     unidos
    -0.90
     блу
    -0.89
    POSITIVE LOGITS
     that
    1.06
     and
    1.05
    enddate
    1.00
     bijvoorbeeld
    0.96
     meestal
    0.95
    fordshire
    0.95
    の国
    0.95
    jetas
    0.93
     dagelijks
    0.92
    жте
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.