© 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. 10-GEMMASCOPE-RES-131K
    7. 68980
    Prev
    Next
    INDEX
    Explanations

    money market funds

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

    The neuron is keyed to numerical and quantitative expressions (amounts, measurements, fund sizes, numbered identifiers).

    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
     Ministre
    -1.68
     rêver
    -1.63
     victime
    -1.53
    Would
    -1.52
     voud
    -1.52
    糴
    -1.51
    ：……
    -1.50
     goû
    -1.48
    \
    -1.47
     '',
    -1.44
    POSITIVE LOGITS
     with
    1.98
     about
    1.81
     after
    1.77
     they
    1.68
     which
    1.66
     did
    1.63
     using
    1.57
     through
    1.54
     in
    1.53
     such
    1.53
    Activations Density 0.138%

    No Known Activations