© 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. 67278
    Prev
    Next
    INDEX
    Explanations

    cyclosporine immunosuppression therapy

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

    pharmaceutical and immunosuppressant drugs, particularly cyclosporine/cyclosporin.

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

    The neuron detects mentions of the immunosuppressant drug “cyclosporine” (especially “cyclosporine A” and its variants).

    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
     has
    -1.94
     ellos
    -1.50
     Another
    -1.41
    ceae
    -1.35
     gave
    -1.34
     If
    -1.34
     nivel
    -1.33
    _
    -1.33
    (
    -1.31
    𝗢
    -1.30
    POSITIVE LOGITS
    футболка
    1.45
    ）　
    1.38
     クッション
    1.37
     realizando
    1.32
     äusser
    1.30
     verfügen
    1.28
     vínculo
    1.28
     compartida
    1.27
     ネタバレ
    1.27
     marcada
    1.27
    Activations Density 0.074%

    No Known Activations