© 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. 65389
    Prev
    Next
    INDEX
    Explanations

    however, contrast or exception

    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
    [];
    -1.73
    ↵↵↵
    -1.59
     we
    -1.59
    Ꝑ
    -1.53
    𖥧
    -1.52
    NUMX
    -1.45
     to
    -1.45
    значно
    -1.44
    uração
    -1.43
    ↵↵
    -1.42
    POSITIVE LOGITS
    为啥
    1.69
     also
    1.63
     a
    1.55
     člověk
    1.53
    只是一个
    1.51
    寕
    1.50
     detallada
    1.47
    素晴
    1.46
    是怎么
    1.45
     někdo
    1.42
    Activations Density 0.009%

    No Known Activations