© 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. 58459
    Prev
    Next
    INDEX
    Explanations

    self-dual mathematical concepts

    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
    APOR
    -0.78
    連載
    -0.75
    的首
    -0.75
    っ
    -0.71
    Override
    -0.69
     exon
    -0.69
    dog
    -0.69
    endfor
    -0.69
     小説
    -0.69
     разум
    -0.68
    POSITIVE LOGITS
     dual
    3.59
    dual
    3.22
    Dual
    2.94
     Dual
    2.89
     duality
    2.42
     DUAL
    2.33
     duel
    1.86
     complementary
    1.67
     двой
    1.66
    idual
    1.45
    Activations Density 0.054%

    No Known Activations