© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20218
    Prev
    Next
    INDEX
    Explanations

    expressing desire or intention

    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
    囖
    -1.79
     Ответить
    -1.75
    糁
    -1.74
     Perſ
    -1.74
    necessary
    -1.73
    cripts
    -1.72
    earlier
    -1.68
    嚒
    -1.66
     auffi
    -1.66
    鵙
    -1.66
    POSITIVE LOGITS
     which
    2.38
     from
    2.05
     has
    2.02
     when
    1.99
     until
    1.87
     still
    1.83
     started
    1.77
     after
    1.73
    廊下
    1.71
     by
    1.70
    Activations Density 0.017%

    No Known Activations