© 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. 117499
    Prev
    Next
    INDEX
    Explanations

    cost structure

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

    This neuron detects numeric expressions, especially cost or price figures (e.g. numbers and hyphenated number ranges).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     expenses
    -0.94
     expenditures
    -0.78
     gastos
    -0.73
     materiali
    -0.73
    運
    -0.72
    hiculo
    -0.72
     Barcel
    -0.70
     nephew
    -0.69
     expense
    -0.68
     Micha
    -0.68
    POSITIVE LOGITS
     structure
    1.07
     Structure
    1.02
    Structure
    0.87
    structure
    0.87
    STRUCTURE
    0.82
    结构
    0.82
     SAU
    0.81
    Kyr
    0.80
     構造
    0.78
     structures
    0.77
    Activations Density 0.031%

    No Known Activations