© 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. 21529
    Prev
    Next
    INDEX
    Explanations

    hyaluronic acid and hyaluronan

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

    The neuron detects biochemical terms related to hyaluronic acid and similar molecules.

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

    The neuron specifically activates on mentions of “hyaluronic acid” (and its chemical shorthand HA or hyaluronan).

    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
    当然
    -2.50
    但
    -2.22
    就
    -1.99
     But
    -1.91
    他
    -1.84
    ть
    -1.82
    냑
    -1.77
    Donativos
    -1.73
    但是
    -1.73
    獲得
    -1.73
    POSITIVE LOGITS
    俢
    1.82
    ︲
    1.67
    きは
    1.62
    ᯾
    1.55
    当下
    1.53
    给我们
    1.52
     Gelände
    1.51
     informar
    1.50
     gesprek
    1.49
    矫
    1.48
    Activations Density 0.024%

    No Known Activations