© 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. 21854
    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
    僱
    -1.23
    的問題
    -1.13
    Specifik
    -1.13
    ꉂ
    -1.13
    來了
    -1.09
    ⓵
    -1.09
    怎樣
    -1.06
    ・・・・・・・・
    -1.05
     przycis
    -1.04
    Приготовление
    -1.03
    POSITIVE LOGITS
    </h2>
    1.11
    })$,
    0.95
    "]:
    0.92
    ©
    0.91
    三四
    0.90
     as
    0.90
    '],
    0.90
    </b>
    0.89
    佑
    0.88
     the
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.