© 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. 89917
    Prev
    Next
    INDEX
    Explanations

    decentralized power structures

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

    The neuron fires on tokens naming formal governmental or legislative entities and processes—e.g. commissions, constitutions, referendums, elections, government bodies, and their associated titles.

    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
    מוש
    -0.87
     unlaw
    -0.87
     publicly
    -0.79
     grupa
    -0.78
    ocimiento
    -0.78
     Squal
    -0.77
     publics
    -0.77
    Dış
    -0.77
    manha
    -0.77
    ISCHE
    -0.76
    POSITIVE LOGITS
     decentral
    2.67
     decentralized
    1.95
     Decentral
    1.80
     autonomy
    1.61
     dev
    1.42
     devolved
    1.41
     transfers
    1.33
    地方
    1.33
    dec
    1.33
     powers
    1.26
    Activations Density 0.019%

    No Known Activations