© 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. 27338
    Prev
    Next
    INDEX
    Explanations

    Federal Reserve and monetary policy

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

    The main thing this neuron does is find mentions of central banks or the Federal Reserve.

    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
    zzlement
    -1.30
     hohe
    -1.30
    “,
    -1.26
     dokumenti
    -1.24
    ",
    -1.20
    .”
    -1.19
     markiert
    -1.17
     zwykle
    -1.17
    全く
    -1.16
    事が
    -1.16
    POSITIVE LOGITS
     exercices
    1.39
     bact
    1.26
    َم
    1.23
    ִּ
    1.22
     engl
    1.17
     what
    1.13
    ペル
    1.11
    ֶּ
    1.11
    wym
    1.10
    īdz
    1.09
    Activations Density 0.010%

    No Known Activations