© 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. 22-GEMMASCOPE-RES-131K
    4. 33504
    Prev
    Next
    INDEX
    Explanations

    acupuncture procedure

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

    The neuron flags mentions of complementary or alternative therapy modalities (e.g. reflexology, acupuncture, EFT, auriculotherapy).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ּוֹ
    -1.37
    гают
    -1.26
    消失了
    -1.23
     emporter
    -1.21
     ancak
    -1.18
     lähe
    -1.18
    ᾽
    -1.18
     poursuivre
    -1.16
    וֹ
    -1.16
    ִּ
    -1.15
    POSITIVE LOGITS
    ׇ
    1.80
     ویتامین
    1.52
     areas
    1.38
    Źródło
    1.33
    ggak
    1.31
    Xoa
    1.29
     focused
    1.29
     many
    1.27
     felpa
    1.25
    ֺ
    1.22
    Activations Density 0.040%

    No Known Activations