© 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. 80741
    Prev
    Next
    INDEX
    Explanations

    genealogy and ancestor research

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

    The neuron fires on numeric tokens (numbers, especially years and counts).

    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
     TM
    -0.90
    arate
    -0.83
     семи
    -0.78
     guitar
    -0.78
    designer
    -0.77
    metries
    -0.77
     נא
    -0.77
     trademarks
    -0.76
     retrofit
    -0.76
     fuck
    -0.76
    POSITIVE LOGITS
     genealog
    1.51
     Researcher
    1.14
    research
    1.13
     ancestor
    1.13
     ancestors
    1.10
     RESEARCH
    1.09
    Researchers
    1.09
     researchers
    1.08
     araştır
    1.06
    RESEARCH
    1.05
    Activations Density 0.028%

    No Known Activations