© 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. 68855
    Prev
    Next
    INDEX
    Explanations

    ord numbers and abbreviations

    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
    </h4>
    -2.41
    ↵
    -2.03
     destacado
    -1.84
    </strong>
    -1.76
     it
    -1.68
     เรา
    -1.66
     That
    -1.64
    すと
    -1.63
    して下さい
    -1.61
     has
    -1.59
    POSITIVE LOGITS
    izienz
    2.06
    趼
    2.06
    ôgrafia
    2.05
     Atención
    2.02
     allan
    2.02
    鿬
    1.95
     armen
    1.86
    these
    1.86
     leaſt
    1.85
    䥑
    1.84
    Activations Density 0.003%

    No Known Activations