© 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. 22-GEMMASCOPE-RES-131K
    7. 36465
    Prev
    Next
    INDEX
    Explanations

    start of lists or sections

    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
     desafios
    -1.52
     męski
    -1.27
     drewna
    -1.23
     tričko
    -1.22
     białym
    -1.20
     umožňuje
    -1.17
     reír
    -1.13
     просмотра
    -1.05
     controladores
    -1.05
     biały
    -1.03
    POSITIVE LOGITS
     Then
    1.28
    Then
    1.26
     then
    1.21
     również
    1.17
    Sementara
    1.16
     fuper
    1.13
    Meanwhile
    1.09
    緑
    1.09
    一切
    1.07
    同样
    1.07
    Activations Density 0.008%

    No Known Activations