© 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. 86962
    Prev
    Next
    INDEX
    Explanations

    financial debts

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

    The neuron fires strongly on occurrences of the word “debt” (and its plural or fragmented forms), i.e. it detects mentions of debt or indebtedness.

    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
    __":
    -2.14
    阄
    -2.11
     腿
    -2.05
    ."
    -1.97
    癀
    -1.96
    The
    -1.93
     них
    -1.91
     ๆ
    -1.90
    过程中
    -1.88
    を防
    -1.88
    POSITIVE LOGITS
    用
    1.98
    IBLIO
    1.98
    2
    1.88
     orologio
    1.85
    0
    1.84
    即使
    1.73
     setelah
    1.73
     dieci
    1.70
     gatto
    1.70
    可能
    1.65
    Activations Density 0.009%

    No Known Activations