Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 252
    Prev
    Next
    INDEX
    Explanations

    spending and expenditure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    řeb
    -0.84
    onResume
    -0.81
    ્
    -0.79
    🛁
    -0.79
     Duggan
    -0.79
    Unemployment
    -0.78
     都市
    -0.78
    mahaman
    -0.77
    replication
    -0.77
    Geographie
    -0.75
    POSITIVE LOGITS
     spending
    4.91
     expenditure
    4.19
     spend
    4.13
     expenditures
    3.88
    spending
    3.64
    Spending
    3.44
     Spending
    3.42
     spent
    3.38
     spends
    3.36
    spend
    3.27
    Activations Density 0.057%

    No Known Activations