© 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. 105718
    Prev
    Next
    INDEX
    Explanations

    family, lineage, marriage, homeland

    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
    ."
    -2.63
     gewiß
    -2.41
     它
    -2.09
    ↵↵
    -2.03
     These
    -2.02
    ⩴
    -2.02
    )
    -1.98
    !"
    -1.94
     risked
    -1.93
     It
    -1.88
    POSITIVE LOGITS
    D
    2.52
    \
    2.31
    Ꮵ
    2.23
    鐒
    2.05
     bune
    2.03
    {
    2.02
     yelek
    1.95
     المسؤول
    1.93
     ナビ
    1.91
     keter
    1.87
    Activations Density 0.004%

    No Known Activations