© 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. 104199
    Prev
    Next
    INDEX
    Explanations

    Caribbean island 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
     auftreten
    -1.58
    塒
    -1.57
     環境
    -1.55
     画像
    -1.54
    ключение
    -1.54
    selben
    -1.53
     allzu
    -1.47
    Ꮉ
    -1.47
     検索
    -1.45
    Different
    -1.45
    POSITIVE LOGITS
    ',
    1.56
     mar
    1.52
     best
    1.46
     '
    1.45
     de
    1.43
     and
    1.38
    ।
    1.38
     E
    1.33
    :
    1.30
     L
    1.30
    Activations Density 0.007%

    No Known Activations