© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84355
    Prev
    Next
    INDEX
    Explanations

    radiotherapy treatment delivery

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

    medical terminology related to radiation therapy and treatment planning.

    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
     الحكومة
    -0.79
     EDTA
    -0.76
    在你
    -0.75
     OPS
    -0.73
     anthropogenic
    -0.72
     nursery
    -0.69
    噪音
    -0.69
    atika
    -0.69
     ovulation
    -0.69
     والخ
    -0.68
    POSITIVE LOGITS
     radiotherapy
    1.70
     radiation
    1.45
    radiation
    1.41
     Radiation
    1.38
    Radiation
    1.29
     irradiation
    1.20
     treatment
    1.13
     cancer
    1.12
     irradiated
    1.10
    cancer
    1.07
    Activations Density 0.295%

    No Known Activations