© 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. 25875
    Prev
    Next
    INDEX
    Explanations

    aerobic and anaerobic exercise parameters

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

    scientific terminology related to aerobic and anaerobic exercise thresholds.

    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
    raine
    -0.78
     notas
    -0.76
    stützung
    -0.74
    EURO
    -0.73
     EURO
    -0.71
    📃
    -0.70
     secre
    -0.70
    Lá
    -0.69
     nominally
    -0.69
    feuille
    -0.68
    POSITIVE LOGITS
     oxygen
    1.51
     anaerobic
    1.28
     aerobic
    1.20
    oxygen
    1.11
     endurance
    1.08
     venti
    1.06
     VO
    1.05
     Oxygen
    1.04
    erobic
    1.02
    Oxygen
    1.01
    Activations Density 0.098%

    No Known Activations