© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47037
    Prev
    Next
    INDEX
    Explanations

    CT or MRI scans

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     ultrasonic
    -0.81
    ophosphate
    -0.79
    ****
    -0.74
     gehalten
    -0.73
    PW
    -0.73
    HEK
    -0.72
     Creighton
    -0.72
    体系
    -0.72
    sedown
    -0.71
    igi
    -0.71
    POSITIVE LOGITS
     scan
    2.47
     scans
    2.28
    scan
    1.76
     Scan
    1.71
     scanning
    1.69
     SCAN
    1.59
     scanner
    1.55
    SCAN
    1.48
     scanned
    1.38
    Scan
    1.37
    Activations Density 0.114%

    No Known Activations