© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92430
    Prev
    Next
    INDEX
    Explanations

    fund and fund closing

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

    The main thing this neuron does is detect numeric monetary figures (e.g. dollar amounts and large numbers).

    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
     horrific
    -0.77
     severe
    -0.75
     okay
    -0.74
     lavish
    -0.74
     jack
    -0.74
    assioned
    -0.73
     full
    -0.71
     drastic
    -0.71
     detailed
    -0.71
     strange
    -0.71
    POSITIVE LOGITS
     fund
    1.85
     Fund
    1.51
    fund
    1.41
    Fund
    1.34
    基金
    1.25
     FUND
    1.15
     funds
    1.13
     Funds
    1.07
    FUND
    1.04
     fundus
    0.94
    Activations Density 0.020%

    No Known Activations