© 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. 11925
    Prev
    Next
    INDEX
    Explanations

    character and show names

    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
    随后
    -1.16
     både
    -1.14
     then
    -1.14
     Now
    -1.09
     Pasta
    -1.08
    neq
    -1.07
     Но
    -1.07
     Geben
    -1.06
    先生が
    -1.05
     professionali
    -1.05
    POSITIVE LOGITS
    dekor
    1.22
    komplet
    1.21
    saco
    1.21
    strukt
    1.20
     ответствен
    1.20
    bagno
    1.19
    lıyor
    1.18
    饪
    1.16
     new
    1.15
    sortOrder
    1.15
    Activations Density 0.029%

    No Known Activations