© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77064
    Prev
    Next
    INDEX
    Explanations

    rules and ordinances

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

    The neuron fires on numeric and citation tokens in legal/regulatory references (e.g. years, rule numbers, section symbols).

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

    No Comments

    Negative Logits
    GreaterThan
    -0.92
     Act
    -0.80
     Konzept
    -0.75
    Recorder
    -0.75
    song
    -0.68
    orations
    -0.68
    Переваги
    -0.67
    AVL
    -0.67
     ライフ
    -0.67
    jumper
    -0.66
    POSITIVE LOGITS
     Rule
    1.17
     rule
    1.09
     Rules
    1.06
     regla
    1.06
     rules
    1.06
     regulations
    1.03
     RULES
    1.02
     RULE
    0.99
     CCR
    0.98
     getRule
    0.97
    Activations Density 0.013%

    No Known Activations