© 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. 34-GEMMASCOPE-RES-131K
    7. 47439
    Prev
    Next
    INDEX
    Explanations

    costs and expenses

    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
     encantó
    -1.13
     encantan
    -1.04
    TintMode
    -0.92
     gustó
    -0.89
    Erreferentziak
    -0.85
    olerance
    -0.82
     ธ
    -0.82
    ธอ
    -0.81
    itemView
    -0.80
    Carriera
    -0.77
    POSITIVE LOGITS
     costs
    7.53
     cost
    7.22
     Costs
    5.41
    cost
    5.41
    costs
    5.31
    Costs
    5.13
    Cost
    4.97
     Cost
    4.91
     expenses
    4.56
     expense
    4.50
    Activations Density 0.197%

    No Known Activations