© 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. 98421
    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
    teknik
    -1.20
     what
    -1.18
    tım
    -1.13
     Temos
    -1.13
     October
    -1.08
     vegano
    -1.08
    CHOOL
    -1.07
     mochila
    -1.07
    操
    -1.04
    pagnol
    -1.03
    POSITIVE LOGITS
     of
    1.15
    for
    0.99
     домашних
    0.98
    面白
    0.96
     них
    0.96
     geben
    0.96
     صورة
    0.96
     אחרים
    0.96
     показатели
    0.96
     книга
    0.95
    Activations Density 0.000%

    No Known Activations