© 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. 10-GEMMASCOPE-RES-131K
    7. 123927
    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
     there
    -1.91
     will
    -1.82
     There
    -1.77
    There
    -1.73
     more
    -1.71
     it
    -1.67
    Other
    -1.64
     relentlessly
    -1.56
     if
    -1.54
    </i>
    -1.53
    POSITIVE LOGITS
     fameux
    1.59
     zoude
    1.53
     incrí
    1.52
    Hmmm
    1.52
     savons
    1.52
    
    1.51
     kommende
    1.50
     kiu
    1.49
    訁
    1.44
    岽
    1.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.