© 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. 69835
    Prev
    Next
    INDEX
    Explanations

    races and outcomes

    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
    rawn
    -1.90
    怎么说
    -1.57
    aneity
    -1.55
     tayang
    -1.54
     memanggil
    -1.52
     siè
    -1.52
    臜
    -1.52
     indiquer
    -1.49
     réjou
    -1.48
     besa
    -1.48
    POSITIVE LOGITS
    -
    2.02
     in
    1.75
     ten
    1.66
     about
    1.59
     any
    1.53
     eight
    1.52
     nine
    1.51
     before
    1.42
     four
    1.41
     eighty
    1.41
    Activations Density 0.011%

    No Known Activations