© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116726
    Prev
    Next
    INDEX
    Explanations

    policies and regulations

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

    The neuron is highly sensitive to formal, regulatory and legal terminology.

    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
     Республики
    -0.89
     généralement
    -0.89
     présentant
    -0.88
     Grenzen
    -0.86
     chré
    -0.86
    assigned
    -0.85
    standig
    -0.85
    ྄
    -0.85
     relativement
    -0.85
    atrices
    -0.84
    POSITIVE LOGITS
     guidelines
    1.48
     rule
    1.25
     rules
    1.23
     introduced
    1.20
     regulations
    1.19
     implemented
    1.18
     norms
    1.15
     implementation
    1.05
     provisions
    1.05
     implement
    1.02
    Activations Density 0.027%

    No Known Activations