© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76481
    Prev
    Next
    INDEX
    Explanations

    carbohydrates during exercise

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

    references to nutrition, food, and hydration in athletic or exercise contexts.

    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
    скур
    -0.93
    πουργ
    -0.92
     catalytic
    -0.91
    Smoking
    -0.91
     Smoking
    -0.88
     smoking
    -0.86
     smoke
    -0.85
     Anwar
    -0.84
     کش
    -0.82
     greenhouse
    -0.82
    POSITIVE LOGITS
     carbohydrate
    1.35
     endurance
    1.13
     DURING
    1.13
     carbohydrates
    1.09
    Carbo
    1.06
    carbo
    1.05
     during
    1.02
     consume
    1.00
     recovery
    1.00
     race
    0.98
    Activations Density 0.031%

    No Known Activations