© 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. 30422
    Prev
    Next
    INDEX
    Explanations

    pay costs

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

    The neuron strongly activates on numeric tokens (digits, numbers, monetary amounts, dates, section or rule numbers).

    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
    허
    -0.80
    카
    -0.80
     encantó
    -0.78
    
    -0.77
     acquisto
    -0.76
     McKinsey
    -0.76
     fã
    -0.75
    merchant
    -0.74
     آش
    -0.73
     confronti
    -0.72
    POSITIVE LOGITS
     costs
    2.78
     Costs
    2.22
    costs
    2.13
    Costs
    2.05
     cost
    1.90
     Cost
    1.49
    cost
    1.48
     COSTS
    1.46
    Cost
    1.46
    COST
    1.38
    Activations Density 0.044%

    No Known Activations