© 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. 102350
    Prev
    Next
    INDEX
    Explanations

    expressing congratulations or wishes

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

    The neuron fires on the formal language of high-level diplomatic congratulations statements (e.g. “[Country] congratulates President-elect X…”)

    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
     either
    -0.94
     that
    -0.88
    Източници
    -0.88
     nějak
    -0.84
     there
    -0.84
    Gön
    -0.83
     krijgen
    -0.82
     ciddi
    -0.82
    がこの
    -0.82
     our
    -0.82
    POSITIVE LOGITS
     particuli
    1.05
     stelle
    0.94
     pray
    0.88
    0.86
     monto
    0.86
    ək
    0.85
    expressed
    0.85
     Fir
    0.85
     Rap
    0.85
    particularly
    0.84
    Activations Density 0.017%

    No Known Activations