© 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. 42052
    Prev
    Next
    INDEX
    Explanations

    Video, winning Ghanaian, buzz, hashtag, known as

    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
     правительства
    -1.59
     so
    -1.48
     it
    -1.48
    尔夫
    -1.47
     And
    -1.32
     этих
    -1.30
     السياس
    -1.30
    ↵
    -1.30
     then
    -1.28
     +
    -1.27
    POSITIVE LOGITS
     ceder
    1.44
     anun
    1.42
     verra
    1.41
    hubaneswar
    1.41
    滏
    1.39
     сахара
    1.39
     legale
    1.38
     velg
    1.38
     dras
    1.38
     dovr
    1.38
    Activations Density 0.025%

    No Known Activations