© 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. 10-GEMMASCOPE-RES-131K
    7. 74771
    Prev
    Next
    INDEX
    Explanations

    Federal Reserve Bank or Register

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

    This neuron activates on mentions of the U.S. central bank (e.g. “Fed,” “Federal Reserve,” “Reserve Bank”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    zzlement
    -1.89
     banyo
    -1.86
    媄
    -1.74
    z
    -1.72
    u
    -1.71
     dekoratif
    -1.69
    塬
    -1.69
     岛
    -1.68
     atau
    -1.65
     навіть
    -1.65
    POSITIVE LOGITS
    ться
    2.19
     you
    2.09
     wichtigste
    1.84
    骓
    1.82
    {
    1.73
    觏
    1.68
    狆
    1.66
    ’
    1.60
    nend
    1.59
    蕺
    1.59
    Activations Density 0.004%

    No Known Activations