© 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. 128157
    Prev
    Next
    INDEX
    Explanations

    capsule medical or time device

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

    The neuron activates for mentions of medical or scientific capsules, particularly in relation to endoscopy and pharmaceutical applications.

    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
     you
    -3.39
    硨
    -3.23
     enthou
    -2.95
    >
    -2.91
    鶫
    -2.86
     decidedly
    -2.77
    賒
    -2.73
    鷙
    -2.66
     tranſ
    -2.63
    
    -2.63
    POSITIVE LOGITS
    <bos>
    3.30
     burgeoning
    3.16
    Ironically
    3.05
    Surprisingly
    3.03
    Shortly
    3.00
    After
    2.98
    Because
    2.91
    During
    2.89
    Following
    2.78
     haphazard
    2.75
    Activations Density 0.011%

    No Known Activations