© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113951
    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
     fullname
    -0.96
     fullName
    -0.94
     different
    -0.93
     mengalir
    -0.88
     einschließlich
    -0.87
     rval
    -0.85
     elems
    -0.85
     creando
    -0.84
     mostrando
    -0.84
     tratando
    -0.84
    POSITIVE LOGITS
     arbitrators
    0.99
    Én
    0.97
     smrti
    0.96
    lação
    0.94
     Organis
    0.91
     Whose
    0.91
    سایت
    0.90
     Estoy
    0.90
     它
    0.89
    если
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.