© 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. 22-GEMMASCOPE-RES-131K
    7. 14891
    Prev
    Next
    INDEX
    Explanations

    cause of death

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

    phrases that describe diseases or conditions as a "leading cause of death".

    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_22/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
     to
    -1.50
    ₩
    -1.05
    汩
    -1.01
    Ț
    -0.98
     semasa
    -0.96
    。
    -0.93
     seier
    -0.93
    斃
    -0.90
     保護
    -0.90
    to
    -0.89
    POSITIVE LOGITS
     both
    1.37
    getMock
    1.19
     in
    1.17
    יהם
    1.11
     combined
    1.09
     silueta
    1.09
     vrá
    1.09
    لكتر
    1.09
     rồng
    1.09
     negru
    1.07
    Activations Density 0.211%

    No Known Activations