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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13129
    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
     litoral
    -1.13
    lijken
    -1.05
    сете
    -1.02
    zionare
    -0.98
     sué
    -0.97
     azulejos
    -0.97
     rosario
    -0.96
     combines
    -0.94
     granada
    -0.94
     lagar
    -0.94
    POSITIVE LOGITS
     and
    1.09
     accogli
    1.05
     trám
    1.00
     plazos
    0.96
     meravigli
    0.93
     begeistert
    0.93
     sellado
    0.93
     ktorá
    0.91
     angebracht
    0.91
     entweder
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.