© 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. 11964
    Prev
    Next
    INDEX
    Explanations

    ages of people

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

    This neuron specifically detects age mentions (numeric age tokens).

    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
     Eighteenth
    -0.81
     that
    -0.81
    比如说
    -0.81
    褔
    -0.77
    特别是
    -0.76
     forerunner
    -0.76
     unresolved
    -0.75
    読み
    -0.75
     Yorkers
    -0.75
     بعض
    -0.74
    POSITIVE LOGITS
    3
    1.02
     young
    0.96
     ۲
    0.96
     tendre
    0.91
     age
    0.90
    4
    0.88
     Nachteile
    0.83
     Lungen
    0.83
     ۳
    0.80
     بتاريخ
    0.80
    Activations Density 0.060%

    No Known Activations