© 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. 60011
    Prev
    Next
    INDEX
    Explanations

    regulatory policy rollback undo

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

    The neuron strongly fires on tokens that are proper nouns or numeric identifiers—that is, capitalized names and numbers.

    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
    ẫn
    -0.94
    __]
    -0.94
     Amend
    -0.94
     Legis
    -0.89
     pořád
    -0.83
    GTK
    -0.81
    generational
    -0.81
     répartition
    -0.80
    "__
    -0.80
    ylated
    -0.78
    POSITIVE LOGITS
     Trump
    1.24
     regulatory
    1.23
     policy
    1.09
     rollback
    1.06
     reinterpret
    1.06
     executive
    1.05
    regulatory
    1.02
     undo
    1.01
    Regulatory
    0.98
     agency
    0.97
    Activations Density 0.036%

    No Known Activations