© 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. 34-GEMMASCOPE-RES-131K
    7. 62432
    Prev
    Next
    INDEX
    Explanations

    diminishing marginal utility of the law

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

    The neuron fires on longer, morphologically complex “content” words—especially technical or abstract terms (e.g. ones ending in –ing, –al, –ity) rather than short function words.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Tô
    -0.82
    כח
    -0.81
    戔
    -0.79
    yethyl
    -0.77
     nă
    -0.77
    Moses
    -0.76
    מנים
    -0.75
    timely
    -0.75
     Ribera
    -0.75
     قی
    -0.74
    POSITIVE LOGITS
     diminishing
    3.73
     returns
    3.08
     Dimin
    2.50
    dimin
    2.48
     Returns
    2.34
    Returns
    2.20
    returns
    2.16
     diminish
    2.02
     diminishes
    1.93
     marginal
    1.92
    Activations Density 0.021%

    No Known Activations