© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65108
    Prev
    Next
    INDEX
    Explanations

    az- words

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

    The neuron fires on occurrences of the substring “azole,” i.e. names of azole‐class antifungal drugs.

    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
     produced
    -0.79
    DESCRIP
    -0.77
    csharp
    -0.74
     ура
    -0.71
    Bm
    -0.71
     Heng
    -0.71
    त्त
    -0.71
     Tornado
    -0.69
    もありました
    -0.68
    Notif
    -0.68
    POSITIVE LOGITS
     Az
    1.21
    Az
    1.04
     AZ
    0.95
    ehr
    0.91
     az
    0.84
     przypadku
    0.83
    imuth
    0.80
    ERTY
    0.78
    AZ
    0.77
    essayer
    0.76
    Activations Density 0.028%

    No Known Activations