© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32682
    Prev
    Next
    INDEX
    Explanations

    selenium and its derivatives

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

    words related to selenium, especially in scientific contexts about nutrition, biochemistry, and glutathione peroxidase.

    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
    ámico
    -0.88
     sätt
    -0.88
    useState
    -0.82
    žo
    -0.81
    Saul
    -0.78
     Menlo
    -0.78
    lné
    -0.78
    Lé
    -0.77
    ッセージ
    -0.77
    Caleb
    -0.77
    POSITIVE LOGITS
     selenium
    1.70
     Selenium
    1.45
     sel
    1.45
    Selenium
    1.37
    selen
    1.22
     Sel
    1.19
    selenium
    1.15
     SEL
    1.05
    Selen
    1.04
     Se
    0.97
    Activations Density 0.059%

    No Known Activations