© 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. 11911
    Prev
    Next
    INDEX
    Explanations

    Q: ... Braising ... Stud ... The Samsung

    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
     or
    -1.51
     While
    -1.48
    ↵
    -1.47
     of
    -1.45
     italiano
    -1.29
     =
    -1.27
    Because
    -1.27
     japones
    -1.26
     от
    -1.26
     externas
    -1.25
    POSITIVE LOGITS
     mostrarán
    1.61
     péné
    1.56
    ೢ
    1.47
     goû
    1.45
     célébr
    1.45
     verrou
    1.44
     imediatamente
    1.43
     necesitan
    1.41
    傒
    1.41
     يول
    1.39
    Activations Density 0.000%

    No Known Activations