© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49095
    Prev
    Next
    INDEX
    Explanations

    epilepsy and antiepileptic drugs

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

    medical terms related to epilepsy and anti-epileptic drug treatments.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron primarily activates on words in the abstract section (the opening summary) of a scientific paper.

    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
    znacz
    -0.86
    сколь
    -0.81
     Volvo
    -0.77
     CVD
    -0.74
    WindowListener
    -0.73
    JP
    -0.71
     Karnataka
    -0.71
     VOC
    -0.70
     GUI
    -0.70
     Buy
    -0.68
    POSITIVE LOGITS
     SUNY
    0.87
     inconsciente
    0.85
     discharges
    0.85
     Haunted
    0.83
    gesi
    0.81
    Gluten
    0.81
    tadora
    0.79
    underlying
    0.78
    Engel
    0.76
     réponses
    0.75
    Activations Density 0.066%

    No Known Activations