© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9009
    Prev
    Next
    INDEX
    Explanations

    identify pneumonia

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

    The neuron lights up on longer, content-rich words—especially multi-syllable nouns, adjectives, or nominalizations (e.g. scientific or technical terms).

    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_24_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
    توى
    0.99
    向け
    0.92
    どう
    0.91
    orneys
    0.89
    楽しみ
    0.89
    ت
    0.88
     Furthermore
    0.87
    นวน
    0.86
     Theoretically
    0.86
    ك
    0.86
    POSITIVE LOGITS
     suspicious
    1.56
     diagnost
    1.49
     detections
    1.48
     diagnosis
    1.45
     diagnose
    1.45
     диагности
    1.45
    诊断
    1.42
     diagnosing
    1.38
     diagnoses
    1.38
     détecter
    1.38
    Activations Density 2.274%

    No Known Activations