© 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. 12222
    Prev
    Next
    INDEX
    Explanations

    creditors and circulatory

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

    The neuron specifically triggers on mentions of “creditors” (parties owed money) in legal or financial contexts.

    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
    岀
    -2.42
    ajuku
    -2.41
    ꜆
    -2.38
    𓆏
    -2.33
     派
    -2.33
     婚礼
    -2.31
    棐
    -2.31
    ustering
    -2.25
     病
    -2.23
    轳
    -2.23
    POSITIVE LOGITS
    0
    3.72
    >
    2.86
    はお
    2.53
    也
    2.52
     
    2.47
    さっき
    2.36
    ープン
    2.25
    不仅
    2.20
     と
    2.20
    對
    2.19
    Activations Density 0.002%

    No Known Activations