© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63528
    Prev
    Next
    INDEX
    Explanations

    Chinese academic journals

    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_34/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
    Гри
    -0.78
     bloating
    -0.77
     vardı
    -0.76
     freq
    -0.75
     Sheryl
    -0.75
     papild
    -0.74
     Campionato
    -0.74
    小說
    -0.73
     oble
    -0.72
    ładka
    -0.71
    POSITIVE LOGITS
     Canal
    0.86
     China
    0.82
     Journal
    0.81
    瞭
    0.79
     Herald
    0.79
     Modern
    0.77
     College
    0.77
     abroad
    0.76
     modern
    0.75
     Foreign
    0.75
    Activations Density 0.017%

    No Known Activations