© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82508
    Prev
    Next
    INDEX
    Explanations

    Dutch/Afrikaans place name fragments

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

    The neuron fires on long, multi-morpheme Dutch/Afrikaans compound nouns (especially place and other proper 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_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
     eenen
    -1.05
     hunne
    -1.05
     schade
    -1.02
     män
    -0.98
     peix
    -0.94
     zijne
    -0.92
     hiel
    -0.89
    Materiaal
    -0.87
    Locatie
    -0.86
     verminder
    -0.85
    POSITIVE LOGITS
     frecuentemente
    0.98
     añad
    0.98
     sumamente
    0.94
     necesariamente
    0.92
     afuera
    0.90
     acostumb
    0.86
     muchísimo
    0.86
     verdaderamente
    0.84
     ursprünglich
    0.82
     caminando
    0.82
    Activations Density 0.029%

    No Known Activations