© 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. 15523
    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
     valgt
    -1.59
     reciclaje
    -1.51
     hospitales
    -1.51
     cómoda
    -1.48
     soldadura
    -1.46
     veículos
    -1.43
     necessità
    -1.39
     tecnologie
    -1.39
     vediamo
    -1.39
     reparación
    -1.37
    POSITIVE LOGITS
     for
    1.95
    }
    1.53
    *
    1.49
    ,
    1.48
     would
    1.48
    ?
    1.48
    <eos>
    1.44
    {
    1.43
    <b>
    1.38
     ,
    1.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.