© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10259
    Prev
    Next
    INDEX
    Explanations

    legumes and soy products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     Cors
    0.85
     Depp
    0.82
     privacy
    0.82
     Privacy
    0.80
     Skeleton
    0.80
    螭
    0.78
     письма
    0.78
    whis
    0.78
     Corte
    0.76
     शार
    0.75
    POSITIVE LOGITS
     legumes
    1.33
     beans
    1.31
    Beans
    1.29
     lentils
    1.29
     legume
    1.27
    豆
    1.23
     Beans
    1.18
     tofu
    1.17
     vegetarian
    1.17
    莢
    1.14
    Activations Density 0.151%

    No Known Activations