© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 81686
    Prev
    Next
    INDEX
    Explanations

    marinade ingredients and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cooked
    0.66
    cooked
    0.58
    ConsoleText
    0.56
     roasted
    0.55
     fried
    0.55
     beans
    0.54
    炖
    0.54
     soup
    0.54
    煮
    0.54
     steamed
    0.53
    POSITIVE LOGITS
     Marin
    0.91
    Marin
    0.89
     marin
    0.88
    marin
    0.82
     marinade
    0.80
    mar
    0.71
     mar
    0.70
     marinated
    0.66
     Mar
    0.64
     Мари
    0.63
    Activations Density 0.048%

    No Known Activations