© 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. 70334
    Prev
    Next
    INDEX
    Explanations

    French physicist Léon

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

    The neuron is primarily responsive to numeric date tokens (e.g. years like “1850s”) and other date‐related numbers.

    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
     Fassung
    -0.83
    hynch
    -0.82
    imab
    -0.79
     nationals
    -0.74
     Taft
    -0.73
     leaflets
    -0.72
    ুল
    -0.72
     宋
    -0.71
    Externé
    -0.71
     Deadpool
    -0.70
    POSITIVE LOGITS
     experiments
    1.02
     Volta
    0.93
     Experiments
    0.92
     experiment
    0.90
     experimental
    0.82
     Alessandro
    0.82
     demonstrations
    0.81
     эксперимента
    0.80
     Dani
    0.78
     Sturgeon
    0.78
    Activations Density 0.045%

    No Known Activations