© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60454
    Prev
    Next
    INDEX
    Explanations

    colons and em dashes

    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
    Опис
    -1.75
     nawet
    -1.53
    伷
    -1.48
     it
    -1.44
    有两
    -1.43
     навіть
    -1.41
     dekoratif
    -1.41
    參考文獻
    -1.41
    nexo
    -1.41
    将在
    -1.41
    POSITIVE LOGITS
     a
    2.34
    ：……
    1.69
    ﹕
    1.47
    </b>
    1.45
     ersten
    1.44
     an
    1.34
     häufig
    1.31
     They
    1.28
     to
    1.26
    凝土
    1.25
    Activations Density 0.059%

    No Known Activations