© 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. 22-GEMMASCOPE-RES-131K
    7. 167
    Prev
    Next
    INDEX
    Explanations

    borrowing and lending money

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

    The neuron strongly activates on words and forms related to borrowing or lending (e.g., borrow, borrowed, lending, loan, lend).

    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
     это
    -1.54
     he
    -1.24
            
    -1.22
    ஂ
    -1.20
     herida
    -1.20
    และ
    -1.18
    ку
    -1.15
    ﮏ
    -1.13
     lakini
    -1.13
     её
    -1.10
    POSITIVE LOGITS
    only
    1.64
     borrowing
    1.58
     搞笑
    1.41
    儇
    1.39
    Heh
    1.38
    borrow
    1.38
     borrow
    1.34
    糁
    1.33
     家居
    1.32
    ?".
    1.31
    Activations Density 0.012%

    No Known Activations