© 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. 1112
    Prev
    Next
    INDEX
    Explanations

    trying delicious food dishes

    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
    ystore
    1.74
     sanitize
    1.73
    텅
    1.73
    ңуз
    1.71
    łych
    1.66
    ześ
    1.63
     Noida
    1.63
     recuerda
    1.62
     промо
    1.62
    ̔
    1.61
    POSITIVE LOGITS
     lectures
    0.85
    晚餐
    0.78
     Philosoph
    0.78
     Afternoon
    0.75
     ales
    0.75
     dinners
    0.74
     Brah
    0.73
     risotto
    0.72
     Fiorent
    0.72
     supper
    0.72
    Activations Density 0.709%

    No Known Activations