© 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. 10-GEMMASCOPE-RES-131K
    7. 129085
    Prev
    Next
    INDEX
    Explanations

    medulla oblongata

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

    The neuron detects anatomical terms related to the brain and spinal cord, particularly focusing on structures like "medullary," "brainstem," and "central nervous system" regions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ୮
    -1.61
     on
    -1.58
    LayoutConstraint
    -1.50
    ጺ
    -1.50
    䜣
    -1.48
    ActionCreators
    -1.42
    urantes
    -1.40
    posted
    -1.39
    ⩕
    -1.38
     månader
    -1.38
    POSITIVE LOGITS
     of
    1.40
     bénéficiaire
    1.34
     finding
    1.34
     สอง
    1.31
     besto
    1.28
    ↵
    1.28
    鹟
    1.27
    Buenas
    1.17
     ordinateur
    1.17
     peli
    1.15
    Activations Density 0.100%

    No Known Activations