© 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. 25611
    Prev
    Next
    INDEX
    Explanations

    budget allocations and appropriations

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

    The neuron detects mentions of money, budgets, or funding—e.g. dollar amounts, “budget,” “funding,” and similar financial terms.

    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
    ຂ
    -0.91
    虻
    -0.84
    ERSHIP
    -0.84
    Выводы
    -0.84
    жие
    -0.84
     EINVAL
    -0.84
    IVO
    -0.82
    Trus
    -0.82
    étricas
    -0.81
     распростра
    -0.81
    POSITIVE LOGITS
     allocated
    3.08
     allocation
    3.05
     budget
    3.05
     allocate
    3.00
     allocations
    2.66
     allocating
    2.61
     budgetary
    2.50
     funding
    2.42
    alloc
    2.41
    budget
    2.38
    Activations Density 0.034%

    No Known Activations