© 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. 34-GEMMASCOPE-RES-131K
    7. 4258
    Prev
    Next
    INDEX
    Explanations

    synonymous world cup copyright

    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
    Cliquez
    -1.02
    적인
    -1.00
    Accès
    -0.98
    Conseils
    -0.95
    rupulous
    -0.94
     eradic
    -0.94
     fervent
    -0.93
     forefront
    -0.92
    catalyst
    -0.90
     fervor
    -0.89
    POSITIVE LOGITS
    arithmetic
    1.07
     ordinarily
    1.02
     debilitating
    1.01
     Thankfully
    1.00
    然後
    0.97
    :))
    0.96
     همه
    0.96
    えて
    0.96
     discernible
    0.95
     thankfully
    0.94
    Activations Density 0.022%

    No Known Activations