© 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. 10-GEMMASCOPE-RES-131K
    7. 44766
    Prev
    Next
    INDEX
    Explanations

    vaccine design and delivery

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

    medical and scientific content related to vaccines and immunology.

    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_10/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
     after
    -1.31
     can
    -1.27
     often
    -1.24
     HttpStatusCode
    -1.21
     cuando
    -1.21
    Спасылкі
    -1.20
     was
    -1.20
     when
    -1.20
     ALWAYS
    -1.16
     innumerable
    -1.16
    POSITIVE LOGITS
     then
    1.66
     armazenamento
    1.33
     remarkably
    1.30
    chure
    1.27
     prepare
    1.26
    であれば
    1.20
    웹
    1.18
     weeks
    1.17
    になれば
    1.16
    </h4>
    1.14
    Activations Density 0.078%

    No Known Activations