© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58192
    Prev
    Next
    INDEX
    Explanations

    long time, years, decades

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

    The neuron fires strongly on expressions of extended time spans—especially "long time," "years," or similar duration references.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     verstär
    -1.59
    雠
    -1.55
    を見ながら
    -1.53
     gegenwär
    -1.52
     ergän
    -1.52
    referred
    -1.50
     ждет
    -1.47
     erweiter
    -1.47
    を変える
    -1.46
    うーん
    -1.45
    POSITIVE LOGITS
     being
    1.63
    Since
    1.46
     Obtén
    1.44
     Ľ
    1.42
    These
    1.39
     and
    1.38
     Ř
    1.34
    那些
    1.31
     having
    1.29
    ↵
    1.28
    Activations Density 0.014%

    No Known Activations