© 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. 73791
    Prev
    Next
    INDEX
    Explanations

    vaccine development and use

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

    the word "vaccine" in medical texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on occurrences of the word “vaccine,” flagging mentions of vaccines in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     \
    -3.88
    /
    -3.23
     '
    -2.80
     are
    -2.67
     You
    -2.67
     cette
    -2.66
     этой
    -2.56
     barbaric
    -2.50
    =\
    -2.48
     comical
    -2.48
    POSITIVE LOGITS
     queridos
    2.58
    ⃚
    2.28
     häufigsten
    2.28
     solicitar
    2.16
     poderosa
    2.14
     извест
    2.13
     considerados
    2.08
     únicas
    2.06
     semelhantes
    2.05
     poderosos
    2.00
    Activations Density 0.008%

    No Known Activations