© 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. 98590
    Prev
    Next
    INDEX
    Explanations

    Formula 1, MLB, soccer, football

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

    The neuron fires on four-digit numeric tokens that look like years.

    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
    recently
    -1.18
     recientes
    -1.05
     недавно
    -1.05
     lately
    -1.04
    Recently
    -1.03
     dirigentes
    -0.96
     reciente
    -0.94
     enfermos
    -0.94
     avoir
    -0.94
     recently
    -0.94
    POSITIVE LOGITS
    melons
    0.91
     should
    0.89
     tenure
    0.83
     career
    0.80
     and
    0.79
     SEDS
    0.77
     could
    0.75
     performance
    0.75
     eyeliner
    0.75
     hornblende
    0.75
    Activations Density 0.038%

    No Known Activations