© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84971
    Prev
    Next
    INDEX
    Explanations

    pandemic, Kawhi, Baker Mayfield

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

    The neuron is specialized to pick out the “-demic” suffix in words (e.g. “pandemic,” “epidemic”), flagging mentions of disease outbreaks.

    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
     as
    -1.63
     and
    -1.55
     with
    -1.46
     on
    -1.36
     in
    -1.23
     new
    -1.23
     both
    -1.21
    reszcie
    -1.20
     końcu
    -1.20
     at
    -1.13
    POSITIVE LOGITS
     maintenant
    1.16
     favoris
    1.16
    很喜欢
    1.13
    Sadly
    1.13
    Seems
    1.13
    ことがあります
    1.12
    mbers
    1.11
    籥
    1.11
     réellement
    1.11
     conserver
    1.10
    Activations Density 0.009%

    No Known Activations