© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83913
    Prev
    Next
    INDEX
    Explanations

    phim, Sua, dac biet

    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_34/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
     Màu
    -1.32
     Máy
    -1.32
    tranh
    -1.30
    nhung
    -1.27
     Thương
    -1.26
     Quý
    -1.22
     Thiết
    -1.21
     Ảnh
    -1.21
     nhung
    -1.19
     Được
    -1.19
    POSITIVE LOGITS
     Directeur
    1.09
    ilustração
    1.09
     lais
    1.06
    ――――
    1.05
    Conclusão
    1.03
     pato
    1.03
    跻
    1.03
     règne
    1.00
    Horário
    1.00
     tradic
    0.99
    Activations Density 0.004%

    No Known Activations