© 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. 31-GEMMASCOPE-2-RES-262K
    7. 199435
    Prev
    Next
    INDEX
    Explanations

    vitamins and precursors found in food

    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_31_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
    鹼
    0.48
     Alkaline
    0.47
     Chloride
    0.46
     electrolyte
    0.45
     refrigerant
    0.45
     વખતે
    0.43
     Onda
    0.42
    __);
    0.42
     Ammonia
    0.42
     anticoag
    0.41
    POSITIVE LOGITS
    Desktop
    0.44
    ცხ
    0.41
     ಆಹಾರ
    0.38
    坞
    0.37
    无法
    0.36
    food
    0.36
     Desktop
    0.36
    Roberts
    0.36
     desktop
    0.35
    vend
    0.35
    Activations Density 0.047%

    No Known Activations