© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128321
    Prev
    Next
    INDEX
    Explanations

    expenses and costs

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

    The neuron fires on financial‐reporting terms—words denoting profit, income, costs, expenses, operating results, and similar business metrics.

    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
     more
    -1.45
     every
    -1.41
    Other
    -1.38
     other
    -1.31
    C
    -1.29
     Maybe
    -1.27
    Maybe
    -1.26
     Other
    -1.23
    Every
    -1.23
     Since
    -1.22
    POSITIVE LOGITS
    蹿
    1.37
    recor
    1.37
    
    1.36
    :"#
    1.34
     simplement
    1.32
    neutron
    1.31
    囮
    1.29
    椋
    1.26
     NATURAL
    1.24
    
    1.24
    Activations Density 0.025%

    No Known Activations