© 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. 38309
    Prev
    Next
    INDEX
    Explanations

    welfare and wellness contexts

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

    The neuron strongly activates on mentions of “welfare” (including in names of welfare programs, funds, or services).

    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
     wonderfully
    -1.03
    先是
    -0.98
     powerfully
    -0.95
     ridiculously
    -0.94
    =[];
    -0.94
    委会
    -0.92
     incredibly
    -0.91
     following
    -0.90
     looming
    -0.89
     largely
    -0.89
    POSITIVE LOGITS
    gms
    1.05
    IMA
    0.97
     Welfare
    0.94
    kHz
    0.93
     it
    0.93
    씹
    0.90
    ^{(
    0.90
    忖
    0.90
    在此
    0.90
     QUEEN
    0.89
    Activations Density 0.007%

    No Known Activations