© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13139
    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
     which
    -2.00
     were
    -1.75
     speziellen
    -1.59
     całym
    -1.52
     to
    -1.51
     each
    -1.51
     that
    -1.50
     durchaus
    -1.48
     last
    -1.47
    ёл
    -1.45
    POSITIVE LOGITS
     Saltar
    1.76
    woman
    1.72
     tylko
    1.61
     câteva
    1.61
     orice
    1.57
    镡
    1.56
     Justiça
    1.55
     envíos
    1.54
    唰
    1.53
    pausal
    1.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.