© 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. 91505
    Prev
    Next
    INDEX
    Explanations

    advanced/metastatic cancer status

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

    medical terminology and clinical trial language related to cancer treatments and studies.

    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
     victorious
    -0.82
    <0xA3>
    -0.81
    出來的
    -0.75
    景點
    -0.75
    ‌هاي
    -0.75
    orton
    -0.74
     '.',
    -0.74
     desertion
    -0.72
    むら
    -0.72
    這麼
    -0.72
    POSITIVE LOGITS
     metastatic
    1.56
     advanced
    1.28
    advanced
    1.12
     refractory
    1.10
     progressed
    1.07
     Advanced
    1.04
     Meta
    0.95
    Advanced
    0.95
    SECOND
    0.88
     pret
    0.88
    Activations Density 0.210%

    No Known Activations