© 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. 34-GEMMASCOPE-RES-131K
    7. 64560
    Prev
    Next
    INDEX
    Explanations

    Declaring DataTables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    шивания
    -0.84
    Burg
    -0.84
    igin
    -0.82
    🏒
    -0.77
     cosplay
    -0.76
    lerim
    -0.75
     Dresses
    -0.73
     Farina
    -0.73
    廊
    -0.72
    gios
    -0.71
    POSITIVE LOGITS
    DataTable
    1.77
     DataTable
    1.74
     dt
    1.48
     ds
    1.36
     table
    1.31
     dataset
    1.22
     dataTable
    1.21
    dt
    1.20
     tables
    1.18
     DataSet
    1.18
    Activations Density 0.077%

    No Known Activations