© 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. 62427
    Prev
    Next
    INDEX
    Explanations

    policy frameworks and regimes

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

    The neuron strongly activates on terms referring to formal rules or frameworks—e.g. legal, regulatory, policy, tax, dispute‐settlement—i.e. mentions of standing laws or policy regimes.

    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
     umgangssprach
    -0.92
    ματος
    -0.81
    UNITS
    -0.78
    的一次
    -0.76
    ῷ
    -0.75
    χεία
    -0.75
    renar
    -0.75
    徜
    -0.75
     europé
    -0.74
    pathic
    -0.74
    POSITIVE LOGITS
     regime
    4.25
    regime
    3.19
     regimes
    3.11
     Regime
    2.80
     framework
    2.64
     régimen
    2.53
     régime
    2.36
     regimen
    2.20
    framework
    1.97
     system
    1.84
    Activations Density 0.034%

    No Known Activations