© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14037
    Prev
    Next
    INDEX
    Explanations

    budget cuts

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

    The neuron activates on mentions of financial cutbacks—especially “budget cuts” or “funding cuts.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Ƒ
    -1.39
    BIDDEN
    -1.21
     کرونا
    -1.21
     ویتامین
    -1.20
    ṝ
    -1.19
    atecas
    -1.18
    datable
    -1.13
     dégustation
    -1.12
    откры
    -1.11
    CodeDom
    -1.10
    POSITIVE LOGITS
     cuts
    1.66
     budget
    1.66
     staff
    1.47
     reductions
    1.46
     funding
    1.36
     reduction
    1.34
     reduced
    1.33
     resources
    1.27
     compared
    1.20
     budgets
    1.20
    Activations Density 0.045%

    No Known Activations