© 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. 72721
    Prev
    Next
    INDEX
    Explanations

    anatomical sheath

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

    The neuron detects the word "sheath" in various medical, biological, and technical contexts.

    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
    the
    -2.78
    $
    -2.61
    莚
    -2.08
     Like
    -2.05
     has
    -2.03
     finds
    -2.00
     Erlebnis
    -2.00
     '
    -2.00
     Also
    -1.99
     immensely
    -1.99
    POSITIVE LOGITS
     nadru
    2.25
     {
    2.22
     Selain
    2.16
    
    2.16
    銫
    2.13
     quieren
    2.09
     querían
    2.09
     pelig
    2.08
    }}
    2.05
     ‘‘
    2.05
    Activations Density 0.009%

    No Known Activations