© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108430
    Prev
    Next
    INDEX
    Explanations

    medical imaging findings

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

    medical imaging terminology and descriptions of radiological findings.

    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
    -0.96
    minaire
    -0.92
     EKG
    -0.86
    tifik
    -0.85
     Familia
    -0.85
    varande
    -0.84
     фотография
    -0.83
     सरकार
    -0.83
     PERIOD
    -0.83
     ジャケット
    -0.83
    POSITIVE LOGITS
     depict
    1.05
     depicting
    1.02
     images
    1.02
     depiction
    1.00
     MR
    0.94
     dedicated
    0.92
     unen
    0.92
     depicted
    0.91
     Kriege
    0.88
     confident
    0.88
    Activations Density 0.399%

    No Known Activations