© 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. 3289
    Prev
    Next
    INDEX
    Explanations

    case report citation

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

    The neuron fires on numeric tokens in scholarly article metadata—e.g. case counts, ages, years, volume/issue numbers, page ranges, or IDs in titles and citations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Geology
    -0.82
     +"
    -0.79
     Ophthalmology
    -0.79
    ❇
    -0.75
     meng
    -0.74
    Исто
    -0.73
     Canadiens
    -0.71
    msg
    -0.70
    駱
    -0.69
    ril
    -0.69
    POSITIVE LOGITS
     Journal
    0.95
     Elixir
    0.86
    weeted
    0.84
     Croatian
    0.81
     Indian
    0.81
    Asian
    0.79
    Journal
    0.79
    petits
    0.78
    ignition
    0.77
     Asian
    0.77
    Activations Density 0.144%

    No Known Activations