© 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. 34-GEMMASCOPE-RES-131K
    7. 117673
    Prev
    Next
    INDEX
    Explanations

    fatty acid

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

    biochemical terms related to fatty acids and lipid metabolism.

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

    The neuron strongly activates on occurrences of “fatty acid” (and close variants) in scientific 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_34/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
     preocupado
    -0.81
     CDC
    -0.81
     democracies
    -0.75
     ascribe
    -0.69
     workouts
    -0.68
    ക്ക്
    -0.67
     gesundheit
    -0.67
    oslav
    -0.66
    ốp
    -0.65
    商家
    -0.65
    POSITIVE LOGITS
     fatty
    1.85
     acids
    1.69
     Fatty
    1.47
     amino
    1.40
    Fatty
    1.26
     acid
    1.12
    acids
    1.09
     fats
    1.05
    amino
    1.00
    FAT
    0.97
    Activations Density 0.127%

    No Known Activations