© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59546
    Prev
    Next
    INDEX
    Explanations

    egg white and yolk

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

    terms related to egg components, particularly egg yolk, whites, and sac structures.

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

    The neuron strongly activates on mentions of “yolk” (and related egg‐yolk terms, e.g., yolk sac, yolk index) in the text.

    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
     Fortunately
    -2.17
    猛地
    -2.06
     Luckily
    -1.99
    ⡪
    -1.98
    {
    -1.98
    麈
    -1.94
    𝑒
    -1.88
    锜
    -1.80
     Thankfully
    -1.80
    があります
    -1.80
    POSITIVE LOGITS
    0
    2.36
    是非常
    2.20
    鵙
    2.08
     Öffnen
    1.91
    2
    1.85
    acterísticas
    1.82
    へ向
    1.80
     ella
    1.79
    を訪
    1.79
     bezw
    1.78
    Activations Density 0.006%

    No Known Activations