© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 15029
    Prev
    Next
    INDEX
    Explanations

    rule of law

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

    The neuron is detecting mentions of legal rules or the phrase “rule of law.”

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ՚
    -1.70
    inerario
    -1.60
    ője
    -1.59
    PostExecute
    -1.59
    сить
    -1.56
    racuda
    -1.55
     nhưng
    -1.55
    sierten
    -1.54
    ‛
    -1.54
     Berikut
    -1.52
    POSITIVE LOGITS
    er
    1.79
    8
    1.76
    1
    1.69
    ot
    1.48
     armée
    1.48
    它的
    1.47
    0
    1.47
    ut
    1.47
    4
    1.44
    at
    1.41
    Activations Density 0.004%

    No Known Activations