© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98498
    Prev
    Next
    INDEX
    Explanations

    water and substances

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

    phrases containing "water and" followed by another substance or element.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hydrology
    -1.25
     hydrological
    -1.19
     hydrologic
    -1.18
     watering
    -1.18
    水分
    -1.16
     hydration
    -1.16
     Hydration
    -1.16
     Waterford
    -1.13
    Watering
    -1.11
    Wasser
    -1.10
    POSITIVE LOGITS
     electricity
    1.27
     Electricity
    1.00
     solids
    0.93
     other
    0.82
     nutrients
    0.82
     soil
    0.81
     electrical
    0.80
    厕
    0.79
    Electricity
    0.79
    electricity
    0.78
    Activations Density 0.064%

    No Known Activations