© 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. 99566
    Prev
    Next
    INDEX
    Explanations

    contrasting statements with "yet"

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    でしたが
    -1.67
    </sup>
    -1.61
    蔼
    -1.59
    鹛
    -1.55
    },
    -1.53
    koszulka
    -1.51
     fű
    -1.49
    terscotch
    -1.47
    柃
    -1.46
     纯
    -1.45
    POSITIVE LOGITS
    ’
    1.58
     acusa
    1.55
     stále
    1.55
     terutama
    1.52
     mantiene
    1.50
    其他
    1.49
     giebt
    1.48
    还不是
    1.48
     sabemos
    1.48
     algunas
    1.48
    Activations Density 0.017%

    No Known Activations