© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48352
    Prev
    Next
    INDEX
    Explanations

    government and legal titles

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

    The neuron fires on mentions of formal organization names and institutional titles (especially government agencies and their acronyms).

    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
     Ministries
    -0.80
    gek
    -0.74
    政府
    -0.73
    📣
    -0.71
    rachtet
    -0.71
    elen
    -0.71
     ablation
    -0.70
    📪
    -0.70
    是非常
    -0.69
     ministries
    -0.69
    POSITIVE LOGITS
     policy
    0.82
    analisi
    0.79
     متن
    0.75
    助理
    0.75
     Assistant
    0.75
     perfect
    0.73
     замести
    0.73
     Deputy
    0.73
     kantoor
    0.72
    աքին
    0.71
    Activations Density 0.063%

    No Known Activations