© 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. 34-GEMMASCOPE-RES-131K
    7. 115510
    Prev
    Next
    INDEX
    Explanations

    lamina propria or cerebellar nuclei

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

    The neuron identifies anatomical structures and tissue layers in medical or scientific texts.

    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_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
    southwest
    -0.94
     southeastern
    -0.91
     vulgaris
    -0.87
     lisesi
    -0.82
     Inici
    -0.81
     escra
    -0.81
     桶
    -0.81
    اااا
    -0.80
     počas
    -0.80
     VUL
    -0.80
    POSITIVE LOGITS
     connective
    1.32
     stro
    1.16
     der
    1.08
     layer
    1.03
     inner
    1.02
     deeper
    1.02
     lamina
    1.01
     outer
    0.96
    dee
    0.96
     sub
    0.94
    Activations Density 0.156%

    No Known Activations