© 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. 92452
    Prev
    Next
    INDEX
    Explanations

    the followed by person or role

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

    The neuron is detecting the definite article “the” (in any capitalization).

    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
     Friedhof
    -0.91
     Secretario
    -0.91
     παιδιά
    -0.86
    もありました
    -0.85
     Buyer
    -0.81
     asistente
    -0.81
    kaya
    -0.80
     इन
    -0.80
     kteří
    -0.80
     fréquent
    -0.80
    POSITIVE LOGITS
     maestro
    1.80
     singer
    1.78
    这位
    1.66
     his
    1.65
     actor
    1.59
     veteran
    1.52
     rapper
    1.48
     former
    1.45
     billionaire
    1.43
     professor
    1.39
    Activations Density 0.073%

    No Known Activations