© 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. 67388
    Prev
    Next
    INDEX
    Explanations

    glycerol and lipids

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

    The neuron activates for chemical compounds ending in "ol" such as glycerol, alcohol, and polyol.

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

    The neuron detects mentions of glycerol‐based lipid compounds (e.g. “diacylglycerol,” “glycero-3-phospho…glycerol,” etc.).

    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
    e
    -3.14
    as
    -3.02
    身的
    -2.31
     ſont
    -2.30
     horrifying
    -2.28
     Other
    -2.27
     were
    -2.25
    a
    -2.23
     ridiculous
    -2.20
    ا
    -2.20
    POSITIVE LOGITS
     If
    3.00
    ol
    2.75
    猻
    2.53
    ꪔ
    2.31
    秝
    2.30
    琹
    2.11
     lendemain
    2.08
    請繼續
    2.08
    釤
    2.06
    (
    2.05
    Activations Density 0.035%

    No Known Activations