© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4353
    Prev
    Next
    INDEX
    Explanations

    Nunavut and Nunn

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

    The neuron fires on tokens containing the letter sequence “nun” (e.g. parts of “Nunavut,” “Nunn,” or “nuns”).

    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
    Hebrew
    -0.72
     року
    -0.69
     mailbox
    -0.68
    Observers
    -0.68
    וב
    -0.67
    zensionen
    -0.67
    İR
    -0.67
     increasing
    -0.65
     menyenangkan
    -0.65
    oustic
    -0.64
    POSITIVE LOGITS
     Nun
    1.14
    nery
    1.04
    Nun
    1.01
    cio
    0.94
    plets
    0.86
     Kola
    0.83
    унк
    0.81
    rator
    0.79
    neries
    0.79
    quam
    0.78
    Activations Density 0.019%

    No Known Activations