© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44386
    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
    0
    -1.70
    čnosti
    -1.68
    または
    -1.66
    他们
    -1.57
    或
    -1.55
     görd
    -1.53
     ultimi
    -1.51
     или
    -1.49
    Germania
    -1.48
    Gön
    -1.48
    POSITIVE LOGITS
    te
    2.02
     hundred
    1.91
    ons
    1.84
    _
    1.84
     Also
    1.82
    li
    1.70
    al
    1.64
     dozen
    1.63
    を行い
    1.60
     million
    1.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.