© 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. 22-GEMMASCOPE-RES-131K
    7. 64608
    Prev
    Next
    INDEX
    Explanations

    occupations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     wahrscheinlich
    -1.00
     beig
    -0.96
     eld
    -0.91
    b
    -0.91
    ynthia
    -0.90
    ينج
    -0.89
     сзади
    -0.89
    ЕНЬ
    -0.88
    baute
    -0.88
    Some
    -0.87
    POSITIVE LOGITS
     extraordinaire
    1.40
     parroquia
    1.13
     himself
    1.12
     InputDecoration
    1.09
     tradução
    1.06
     lâmpada
    1.05
     ٢
    1.04
     Alamofire
    1.02
    ensiva
    1.02
     método
    1.02
    Activations Density 0.024%

    No Known Activations