© 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. 45415
    Prev
    Next
    INDEX
    Explanations

    radiation dose, exposure, and protection

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

    terms related to radiation exposure, dosimetry, and protection in scientific/medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to technical, quantitative radiation‐protection content—especially numeric values, units, and regulatory citations around radiation shielding, exposure, and dosage.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    veled
    -0.82
    rektur
    -0.75
     AAC
    -0.75
    atico
    -0.71
    heading
    -0.71
    AAC
    -0.70
    imba
    -0.67
    writeObject
    -0.67
     condición
    -0.67
    Executor
    -0.67
    POSITIVE LOGITS
     radiation
    1.71
     Radiation
    1.55
    radiation
    1.47
    Radiation
    1.46
     dose
    1.41
    dose
    1.23
     doses
    1.21
    辐射
    1.20
    Dose
    1.06
     Dose
    1.05
    Activations Density 0.121%

    No Known Activations