© 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. 90
    Prev
    Next
    INDEX
    Explanations

    nex or finale

    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
    鑁
    -3.36
    lgari
    -3.00
    曏
    -2.98
     рассказывает
    -2.86
    ︕
    -2.66
     знал
    -2.61
     которы
    -2.58
     видел
    -2.52
    褔
    -2.52
    泅
    -2.48
    POSITIVE LOGITS
    2
    2.47
    );
    2.38
    //
    2.38
    i
    2.34
    лил
    2.30
    s
    2.28
    了一
    2.23
    ༛
    2.22
     также
    2.19
    4
    2.16
    Activations Density 0.003%

    No Known Activations