© 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. 116646
    Prev
    Next
    INDEX
    Explanations

    years of marriage and anniversaries

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

    The neuron strongly activates on numeric tokens (digits, numbers, and numeric dates/durations).

    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
    这两
    -0.81
    ガール
    -0.80
    amzn
    -0.80
    levelse
    -0.79
    НУ
    -0.78
     均
    -0.75
    号码
    -0.75
     in
    -0.73
    скур
    -0.71
    明け
    -0.71
    POSITIVE LOGITS
     marriage
    1.91
     marital
    1.80
     married
    1.78
     anniversary
    1.74
    marital
    1.42
    married
    1.40
    Marriage
    1.28
    Married
    1.28
     Anniversary
    1.27
     wed
    1.24
    Activations Density 0.013%

    No Known Activations