© 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. 23714
    Prev
    Next
    INDEX
    Explanations

    Also Available, Significance of, regulatory framework

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

    The neuron activates on formal economic or policy–related terminology (e.g. regulatory, procurement, financial, capacity).

    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
     economic
    -0.78
    Yard
    -0.73
     Repar
    -0.71
    腎
    -0.71
     diserta
    -0.71
    ॠ
    -0.68
    olé
    -0.68
     Juris
    -0.68
    勿
    -0.67
     soon
    -0.67
    POSITIVE LOGITS
    logfile
    0.87
     jednej
    0.85
    artifacts
    0.82
     mafia
    0.82
    štění
    0.81
     contract
    0.80
     juges
    0.79
     Obtain
    0.79
     pierwszej
    0.76
     AVAILABLE
    0.76
    Activations Density 0.003%

    No Known Activations