© 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. 113345
    Prev
    Next
    INDEX
    Explanations

    idiopathic interstitial pneumonias

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

    scientific terms related to medical conditions and chemical compounds.

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

    The neuron activates on specialized scientific or medical terms—particularly long chemical compound names and complex disease or technical jargon.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ﻂ
    -2.13
    剜
    -1.98
    
    -1.91
    槑
    -1.85
    溦
    -1.81
     ſie
    -1.75
    呔
    -1.73
     overly
    -1.73
    看著
    -1.70
     लेकिन
    -1.69
    POSITIVE LOGITS
    ↵↵
    2.33
    {
    1.87
     Its
    1.82
     To
    1.81
     mempunyai
    1.75
     you
    1.74
    ၆
    1.73
    n
    1.70
    nın
    1.66
    .
    1.66
    Activations Density 0.028%

    No Known Activations