© 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. 21679
    Prev
    Next
    INDEX
    Explanations

    financial burdens and overheads

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

    The neuron detects terms that denote financial burdens or encumbrances—words referring to debt, leverage, overhead, encumbrance, and similar cost-related loads.

    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
    ꜆
    -2.02
     nimmer
    -1.84
    %")
    -1.74
     behandelt
    -1.72
    believe
    -1.68
    "`
    -1.66
    〉
    -1.63
    perhaps
    -1.58
    "$
    -1.54
     })
    -1.53
    POSITIVE LOGITS
     on
    2.16
     with
    1.74
     excessively
    1.58
     not
    1.49
     >
    1.48
     extraordinarily
    1.48
     tries
    1.45
     extraordinary
    1.44
     extravagant
    1.44
     strives
    1.41
    Activations Density 0.030%

    No Known Activations