© 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. 94233
    Prev
    Next
    INDEX
    Explanations

    principles, rules, equations, govern

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

    The neuron activates on legal/licensing terminology (words like “license,” “agreement,” “EULA,” “terms,” “conditions,” etc.).

    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
    праж
    -0.89
    mordial
    -0.76
     chromosome
    -0.75
    Steg
    -0.75
    initely
    -0.74
     TAMBIÉN
    -0.73
     concorso
    -0.73
    DialogComponent
    -0.73
    klad
    -0.72
    pense
    -0.71
    POSITIVE LOGITS
     governing
    4.63
     govern
    4.19
     governs
    4.06
    gover
    3.59
     governed
    3.22
     Governing
    3.20
    Governing
    3.09
    govern
    2.92
     regulating
    2.88
     GOVERN
    2.86
    Activations Density 0.145%

    No Known Activations