© 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. 83193
    Prev
    Next
    INDEX
    Explanations

    names of people

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

    The neuron fires on occurrences of “Dion” (or extended forms like Dionisio, Dionys, etc.) within names or words.

    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
     určit
    -0.75
    Eure
    -0.73
     pronta
    -0.66
    ujte
    -0.66
    alni
    -0.65
    다는
    -0.63
    Virt
    -0.63
     उद
    -0.62
     entered
    -0.62
    nocześnie
    -0.62
    POSITIVE LOGITS
    iscus
    0.94
    sius
    0.91
    uis
    0.86
    piller
    0.80
     Xavier
    0.80
    xtra
    0.79
     drehen
    0.76
     Cisco
    0.75
    chiere
    0.74
    adır
    0.73
    Activations Density 0.038%

    No Known Activations