© 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. 93600
    Prev
    Next
    INDEX
    Explanations

    medical field and institution names

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

    the word "Medical" in professional and institutional contexts.

    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
     Corrosion
    -0.77
    iliation
    -0.77
     oblige
    -0.75
     Gebä
    -0.75
    CASCADE
    -0.74
    държа
    -0.73
    antico
    -0.73
     recited
    -0.71
    quarie
    -0.70
     pouvons
    -0.69
    POSITIVE LOGITS
     sciences
    0.80
     Grimes
    0.78
     Broadway
    0.76
    toMatchSnapshot
    0.76
    Superintendent
    0.73
    bulos
    0.72
     Stars
    0.72
     Schumacher
    0.71
     Eagles
    0.71
     superintendent
    0.70
    Activations Density 0.035%

    No Known Activations