© 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. 9124
    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
    ポイントは
    -1.78
    資料來源
    -1.59
     Aloe
    -1.48
    —(
    -1.48
    Kako
    -1.48
    derdag
    -1.47
    <bos>
    -1.45
    还挺
    -1.42
    鱟
    -1.39
    鼱
    -1.39
    POSITIVE LOGITS
     That
    2.08
    」
    1.94
     zarówno
    1.66
     която
    1.66
    фай
    1.62
    enschappen
    1.61
    complish
    1.59
    燔
    1.57
     "")
    1.57
     ``
    1.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.