© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7113
    Prev
    Next
    INDEX
    Explanations

    foreign words and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite

    5 minutes or disclaimer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ab
    0.52
    S
    0.50
    ert
    0.48
    m
    0.48
    b
    0.47
    ak
    0.45
    aji
    0.44
    k
    0.43
    withstanding
    0.43
    ua
    0.43
    POSITIVE LOGITS
     разных
    0.61
     Edith
    0.54
    фан
    0.51
     різних
    0.51
     çal
    0.49
     Mantel
    0.48
     różnych
    0.47
     ersche
    0.47
     część
    0.46
     cambiamenti
    0.46
    Activations Density 0.000%

    No Known Activations