© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3598
    Prev
    Next
    INDEX
    Explanations

    foreign language words and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
     legions
    1.33
     Mindanao
    1.32
     turno
    1.30
    DEF
    1.29
    inado
    1.29
     ثانوي
    1.28
     comest
    1.28
    鍾
    1.27
    ił
    1.27
     diperlukan
    1.27
    POSITIVE LOGITS
    publisher
    0.97
     Meta
    0.96
    ounc
    0.95
    publishing
    0.94
    宇
    0.91
     ITA
    0.89
    atoare
    0.89
    Maur
    0.89
     imputation
    0.88
    парат
    0.87
    Activations Density 0.029%

    No Known Activations