© 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. 20050
    Prev
    Next
    INDEX
    Explanations

    describing size (large, tiny, huge)

    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
    這
    -1.77
    これ
    -1.68
    それは
    -1.47
     Partagez
    -1.46
    Cuáles
    -1.46
     ”
    -1.46
    这
    -1.45
     burbu
    -1.41
     solcher
    -1.41
     saul
    -1.40
    POSITIVE LOGITS
     atau
    1.80
     или
    1.68
    ᨕ
    1.53
     особенно
    1.48
     lanzó
    1.47
     help
    1.47
     například
    1.47
     entrado
    1.44
     your
    1.43
     takže
    1.42
    Activations Density 0.045%

    No Known Activations