© 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. 38519
    Prev
    Next
    INDEX
    Explanations

    so-called

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

    This neuron specifically fires on instances of the phrase “so-called.”

    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
    拄
    -0.98
     griechischen
    -0.91
    aneity
    -0.91
    Semua
    -0.88
    (ﾟ
    -0.87
     both
    -0.86
    それぞれ
    -0.86
    sarung
    -0.85
    および
    -0.85
     roughly
    -0.85
    POSITIVE LOGITS
     called
    2.95
    called
    2.39
    Called
    2.05
     llamados
    1.93
     Called
    1.91
     llamado
    1.87
     chamada
    1.85
     называется
    1.81
     llamada
    1.80
     chamado
    1.61
    Activations Density 0.011%

    No Known Activations