© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12840
    Prev
    Next
    INDEX
    Explanations

    weight loss ingredients

    np_acts-logits-general · gemini-2.5-flash-lite

    ingredients and stimulants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    倫
    0.48
     سام
    0.44
    橛
    0.43
    開設
    0.43
    觀眾
    0.42
    遜
    0.42
     مریض
    0.42
    樹
    0.42
    廈
    0.42
     امر
    0.41
    POSITIVE LOGITS
    ingredients
    0.61
     ingredientes
    0.61
     ingredients
    0.57
     ingrédients
    0.56
     capsules
    0.55
    ingredient
    0.54
     ingredient
    0.54
     pills
    0.52
    Ingredients
    0.52
    这款
    0.52
    Activations Density 0.074%

    No Known Activations