© 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. 73790
    Prev
    Next
    INDEX
    Explanations

    radiographic

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

    words related to radiology and radiographic imaging in medical contexts.

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

    The neuron detects occurrences of the prefix “radio­–” (as in radiation, radiography, radiomics, radiofrequency, radioiodine, etc.).

    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
     ANI
    -0.79
    Celeste
    -0.75
     conosce
    -0.72
    IMENT
    -0.68
     diperhatikan
    -0.66
    贈
    -0.66
    sekolah
    -0.65
    ʈ
    -0.65
     заниматься
    -0.64
     條
    -0.64
    POSITIVE LOGITS
     occult
    1.01
    opaque
    0.89
     RADIUS
    0.88
    steroids
    0.83
    graphs
    0.80
     opaque
    0.76
    катери
    0.73
     nucleotides
    0.72
    paque
    0.70
    áll
    0.70
    Activations Density 0.060%

    No Known Activations