© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1529
    Prev
    Next
    INDEX
    Explanations

    after age descriptions

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

    The neuron strongly activates on standalone numeric tokens—especially age or year numbers—within obituary‐style notices.

    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
    年龄
    -1.73
    スポンサーリンク
    -1.66
     âge
    -1.53
     âgé
    -1.52
    ――――
    -1.47
    鐽
    -1.46
    ―――
    -1.46
    ＊＊＊＊
    -1.45
    もうすぐ
    -1.44
     parfü
    -1.41
    POSITIVE LOGITS
     of
    3.17
     a
    3.02
     is
    2.41
     was
    2.06
     who
    1.91
     has
    1.77
     and
    1.66
     an
    1.66
     like
    1.63
     left
    1.55
    Activations Density 0.021%

    No Known Activations