© 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. 50514
    Prev
    Next
    INDEX
    Explanations

    isotopic labels in experiments

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

    radioactive isotope labels in scientific research, particularly those marked with [3H] or other isotopes in biochemical studies.

    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
    ptic
    -0.72
    ţii
    -0.70
    ții
    -0.68
    ⼊
    -0.68
     beğ
    -0.67
    iname
    -0.66
     fry
    -0.66
    IVERSITY
    -0.66
    铰
    -0.66
     llaves
    -0.65
    POSITIVE LOGITS
     ${
    2.77
     radioactive
    2.27
     radio
    2.16
    ${
    2.16
    radio
    1.84
    <sup>
    1.83
     labeled
    1.77
     радио
    1.73
     labelled
    1.71
    Radio
    1.67
    Activations Density 0.416%

    No Known Activations