© 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. 9598
    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
     That
    -2.38
    that
    -2.22
    瞜
    -2.11
    我已经
    -1.79
     They
    -1.77
    шая
    -1.74
    黽
    -1.74
     که
    -1.74
    ：【
    -1.71
     However
    -1.70
    POSITIVE LOGITS
    ',
    1.88
    ↵↵
    1.79
    噤
    1.72
    <
    1.69
     urod
    1.68
    ch
    1.66
    ?
    1.66
    痞
    1.62
     solicitar
    1.61
     небольшой
    1.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.