© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10587
    Prev
    Next
    INDEX
    Explanations

    hydration and fluid intake

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

    hydration and drinking

    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_40_width_16k_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
     quarry
    0.46
     شکار
    0.45
     Quarry
    0.44
    悻
    0.43
    EnumType
    0.42
    טת
    0.41
     وفر
    0.40
    疳
    0.40
    нням
    0.40
    Diesel
    0.39
    POSITIVE LOGITS
     hydration
    2.39
     dehydration
    2.19
     hydrating
    2.13
    hydration
    2.08
     hydrated
    2.06
     dehydrated
    2.03
     dehyd
    1.99
     hydrate
    1.97
     hydrates
    1.95
     hidrat
    1.95
    Activations Density 0.304%

    No Known Activations