© 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. 10-GEMMASCOPE-RES-131K
    7. 65102
    Prev
    Next
    INDEX
    Explanations

    life events and ceremonies

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

    This neuron responds to words naming celebrations, ceremonies, or milestone events (e.g. Sweet Sixteen, birthday party, baby shower, baptism, confirmation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    only
    -1.66
    8
    -1.59
    ఽ
    -1.58
    ョン
    -1.55
    alakip
    -1.55
    9
    -1.54
     ráp
    -1.52
    the
    -1.50
    D
    -1.48
    wezen
    -1.46
    POSITIVE LOGITS
    ဴ
    1.51
    ႏ
    1.47
     aumentare
    1.40
    硖
    1.34
     tämän
    1.34
     zowel
    1.33
     materi
    1.33
    𓐍
    1.32
    ión
    1.27
     crescere
    1.27
    Activations Density 0.005%

    No Known Activations