© 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. 22-GEMMASCOPE-RES-131K
    7. 73653
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    лови
    -0.93
    の説明
    -0.93
     nowych
    -0.92
     partagé
    -0.91
     informacion
    -0.90
     '{@
    -0.89
    س
    -0.89
     Economía
    -0.88
     descripcion
    -0.86
     Administración
    -0.86
    POSITIVE LOGITS
     with
    1.27
     and
    1.19
     without
    0.89
     suicidio
    0.88
     ['',
    0.88
    ărilor
    0.88
     weakly
    0.87
    étisme
    0.87
     bior
    0.86
     murieron
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.