© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63792
    Prev
    Next
    INDEX
    Explanations

    fat sculpting and cosmetic procedures

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

    medical and anatomical terms, particularly those related to tissue, cells, and surgical procedures.

    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
    副本
    -0.77
     metallo
    -0.75
     inoc
    -0.74
    GOS
    -0.74
     pouss
    -0.72
     eyelashes
    -0.72
     ناش
    -0.70
     Schlegel
    -0.70
     aula
    -0.69
    GOP
    -0.68
    POSITIVE LOGITS
    scul
    1.17
     fat
    1.15
    Scul
    1.11
     Scul
    1.05
     cryo
    1.05
     lipos
    0.99
     contour
    0.96
     lipo
    0.95
    fat
    0.90
     Lipo
    0.90
    Activations Density 0.013%

    No Known Activations