© 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. 86867
    Prev
    Next
    INDEX
    Explanations

    brain imaging techniques

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

    medical imaging techniques like MRI, PET, CT scans, and neuroimaging terminology.

    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
     叶子
    -0.89
     töd
    -0.77
     Micron
    -0.73
     surfboard
    -0.72
     экран
    -0.72
     erreich
    -0.69
     Лин
    -0.69
     مين
    -0.69
     foldable
    -0.69
     ترك
    -0.69
    POSITIVE LOGITS
     MRI
    3.33
    MRI
    2.86
     fMRI
    2.45
     Magnetic
    2.31
     magnetic
    2.31
     NMR
    2.31
     PET
    2.20
    Magnetic
    2.08
    NMR
    1.92
     MR
    1.83
    Activations Density 0.327%

    No Known Activations