© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2046
    Prev
    Next
    INDEX
    Explanations

    financial and mathematical notation

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

    The neuron is highly selective for the standard supplement/drug‐disclaimer phrase “diagnose, cure or prevent” (as in “not intended to diagnose, cure or prevent disease”).

    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
    トラック
    -0.74
     בכ
    -0.70
     Thorn
    -0.69
    nj
    -0.69
     získ
    -0.69
    璉
    -0.68
     BK
    -0.66
     venous
    -0.65
     Marlow
    -0.65
     Tack
    -0.65
    POSITIVE LOGITS
     it
    0.75
     shortcut
    0.73
     adventure
    0.67
     oc
    0.67
    ิจ
    0.65
    眺
    0.65
    اسة
    0.63
     connect
    0.63
    一部
    0.62
    転
    0.62
    Activations Density 0.051%

    No Known Activations