© 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. 22-GEMMASCOPE-RES-131K
    7. 12756
    Prev
    Next
    INDEX
    Explanations

    specific populations or demographics

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

    The neuron activates on quantitative outcome numbers and statistical measures (e.g. mortality rates, incidence values, scores) in clinical or scientific 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_22/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
     other
    -0.94
     tuturor
    -0.84
     दूसरे
    -0.81
    ობ
    -0.79
     autres
    -0.79
    *{\
    -0.79
     Others
    -0.77
    cort
    -0.77
    lijker
    -0.77
     Merger
    -0.76
    POSITIVE LOGITS
     specifically
    1.33
     specific
    1.28
     riêng
    1.27
    Specifically
    1.23
     especially
    1.20
    specific
    1.19
     отдельно
    1.18
    单独
    1.06
     particular
    1.05
    SPECIFIC
    1.05
    Activations Density 0.093%

    No Known Activations