© 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. 10099
    Prev
    Next
    INDEX
    Explanations

    ancient origins and history

    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
     craz
    -2.80
     صفحۀ
    -2.47
    蟥
    -2.45
    ༷
    -2.44
    棡
    -2.39
     mangled
    -2.36
    を入れる
    -2.36
     Projektu
    -2.33
    十分的
    -2.27
     “
    -2.20
    POSITIVE LOGITS
    ↵
    4.09
    т
    2.92
    P
    2.92
    禤
    2.80
     undoubtedly
    2.77
     —
    2.75
     strangely
    2.66
     unparalleled
    2.61
    AN
    2.58
     relatively
    2.56
    Activations Density 0.003%

    No Known Activations