© 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. 10-GEMMASCOPE-RES-131K
    7. 75032
    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
     моя
    -1.21
     kako
    -1.18
    e
    -1.16
    一亮
    -1.16
    i
    -1.14
    îte
    -1.10
     cuna
    -1.10
    恼
    -1.09
     siyang
    -1.09
     настройки
    -1.08
    POSITIVE LOGITS
    ’
    1.38
    Selain
    1.32
    ъм
    1.23
    kowanie
    1.20
     However
    1.19
    A
    1.16
    irinha
    1.15
    InlineData
    1.13
     addition
    1.13
     Luckily
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.