© 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. 21579
    Prev
    Next
    INDEX
    Explanations

    ancient greece, plato, and aristotle

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

    The neuron fires strongly on terms related to Greek (especially classical or ancient Greek) contexts and names.

    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
     predecess
    -1.62
    啣
    -1.61
     pastillas
    -1.59
     eſſ
    -1.53
    䴀
    -1.50
     fantasi
    -1.48
    漼
    -1.47
     iniqu
    -1.46
    儇
    -1.45
     called
    -1.45
    POSITIVE LOGITS
     both
    1.77
     even
    1.56
     reação
    1.45
     only
    1.43
     condição
    1.37
     by
    1.34
     asesinado
    1.33
     on
    1.32
     at
    1.27
    ↵↵
    1.26
    Activations Density 0.106%

    No Known Activations