© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1672
    Prev
    Next
    INDEX
    Explanations

    food items involving orders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
    🏺
    0.74
    Wine
    0.67
    ワイン
    0.66
     Wine
    0.65
     wijn
    0.63
    rystalline
    0.62
    🧘
    0.62
    metast
    0.60
    酒
    0.60
    Tinh
    0.59
    POSITIVE LOGITS
     burger
    1.72
     burgers
    1.53
     fries
    1.45
     fried
    1.42
    Burger
    1.42
     grilled
    1.41
     patty
    1.41
     patties
    1.41
     Burger
    1.35
     hamburger
    1.33
    Activations Density 0.627%

    No Known Activations