© 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. 25186
    Prev
    Next
    INDEX
    Explanations

    java.util.List declarations

    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
     Serviço
    -1.01
    浚
    -1.00
    ctober
    -0.99
    резать
    -0.97
     in
    -0.95
     While
    -0.94
    ždy
    -0.90
    🛵
    -0.90
     Krankenhaus
    -0.89
     Theologie
    -0.88
    POSITIVE LOGITS
     élar
    1.19
     you
    1.09
     comunión
    1.05
    夘
    1.04
     которые
    1.04
     rehabilitación
    1.03
     wielu
    1.02
     kilku
    1.02
     przygoto
    1.01
     étan
    1.01
    Activations Density 0.001%

    No Known Activations