© 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. 34-GEMMASCOPE-RES-131K
    7. 91643
    Prev
    Next
    INDEX
    Explanations

    loan and borrow activities

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

    The neuron strongly activates on words and contexts having to do with lending or borrowing—e.g. “on loan,” “loaners,” “borrowed money,” etc.

    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
    канал
    -0.81
    SNP
    -0.70
    DHA
    -0.69
     kaart
    -0.69
     Cornish
    -0.69
    ERP
    -0.68
    bulk
    -0.66
    architecte
    -0.66
    zki
    -0.65
    Cliquez
    -0.65
    POSITIVE LOGITS
     loan
    5.91
     borrow
    5.16
     borrowed
    5.09
     loaned
    5.09
     borrowing
    4.81
    loan
    4.69
    Loan
    4.63
     loans
    4.53
    borrow
    4.53
     Loan
    4.47
    Activations Density 0.085%

    No Known Activations