© 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. 116827
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     so
    -1.24
    bigr
    -0.98
     Так
    -0.98
    expiresIn
    -0.96
    mappedBy
    -0.94
    となりました
    -0.93
     whoſe
    -0.93
     levert
    -0.90
    dailymail
    -0.90
     šte
    -0.85
    POSITIVE LOGITS
    ra
    0.99
    umán
    0.95
     eventuell
    0.94
    tics
    0.94
    লা
    0.93
    heses
    0.93
    {~
    0.90
     ребё
    0.90
     ().
    0.90
    铝
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.