© 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. 9233
    Prev
    Next
    INDEX
    Explanations

    endings of words

    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
    幾天
    -1.25
    ilarang
    -1.20
     companies
    -1.20
     firms
    -1.19
     으로
    -1.17
    に入って
    -1.16
    ùy
    -1.15
    첫
    -1.15
    了一個
    -1.15
     을
    -1.14
    POSITIVE LOGITS
    while
    1.18
    āra
    1.16
     mentre
    1.13
    нні
    1.13
    身体
    1.10
    xmlWriter
    1.09
     demás
    1.08
     canzoni
    1.08
     you
    1.04
    sise
    1.04
    Activations Density 0.177%

    No Known Activations