© 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. 22-GEMMASCOPE-RES-131K
    7. 128493
    Prev
    Next
    INDEX
    Explanations

    Roman numerals, abbreviations, or lists

    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_22/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
     update
    -1.15
     ποι
    -1.12
     it
    -1.05
    ၀
    -1.04
     sesuai
    -1.04
     and
    -1.03
     focused
    -1.00
    であり
    -0.96
     Update
    -0.95
     link
    -0.95
    POSITIVE LOGITS
     کردند
    1.34
    丹药
    1.16
     prêtre
    1.16
    cythe
    1.13
    枱
    1.09
     озеро
    1.09
     outono
    1.07
    ჱ
    1.06
    妧
    1.06
     estampado
    1.06
    Activations Density 0.017%

    No Known Activations