© 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. 10-GEMMASCOPE-RES-131K
    7. 113513
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     especial
    -1.13
     incluse
    -1.09
    indicate
    -0.97
     elit
    -0.95
     ofer
    -0.94
     strategie
    -0.94
     muda
    -0.93
     recomand
    -0.93
     puedo
    -0.91
    久しぶりに
    -0.91
    POSITIVE LOGITS
    elezo
    0.96
    骠
    0.94
    Hats
    0.94
    leggio
    0.91
     dirigido
    0.91
     mistrzost
    0.91
    langsung
    0.90
     hidrá
    0.89
    poison
    0.86
    mails
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.