© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9124
    Prev
    Next
    INDEX
    Explanations

    cases and patients

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

    The neuron primarily detects numeric tokens representing data values (e.g. counts, measurements, percentages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trillions
    0.64
    每年
    0.63
     tahun
    0.63
     années
    0.62
    ในปี
    0.61
     annually
    0.60
     বছরে
    0.60
    倪
    0.60
     வருட
    0.59
     ahorrar
    0.59
    POSITIVE LOGITS
     cases
    1.15
     Cases
    1.08
     casos
    1.07
    cases
    1.05
     కేసులు
    1.04
    病例
    0.98
     kasus
    0.96
     detections
    0.94
     confirmed
    0.93
     ಪ್ರಕರಣ
    0.92
    Activations Density 0.056%

    No Known Activations