© 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. 102256
    Prev
    Next
    INDEX
    Explanations

    resistance or quantity

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

    nutrition and health

    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
    ০০
    0.47
    公正
    0.46
    いたら
    0.46
     компанией
    0.45
     друзьями
    0.44
    佬
    0.44
    গোল
    0.43
     стол
    0.42
    ка
    0.42
    ติ
    0.41
    POSITIVE LOGITS
     malnutrition
    0.54
     nutritional
    0.52
     և
    0.50
     food
    0.50
     vertebral
    0.48
     thymus
    0.47
     seedlings
    0.47
     hematopoietic
    0.47
     nutritive
    0.47
     nutrient
    0.46
    Activations Density 0.003%

    No Known Activations