© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27676
    Prev
    Next
    INDEX
    Explanations

    cover and pay expenses

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

    This neuron detects verbs that denote providing or obtaining money to cover costs (e.g., pay, cover, support, refund, recover, reimburse).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     именно
    -1.04
    riturismo
    -0.99
    力度
    -0.98
    accuracy
    -0.96
     thi
    -0.95
     at
    -0.95
     acumula
    -0.95
     accuracy
    -0.94
    cimentos
    -0.93
    itteet
    -0.93
    POSITIVE LOGITS
     the
    1.56
     costs
    1.54
     needed
    1.14
     expenses
    1.13
     expédi
    1.13
     cost
    1.10
     phénom
    1.09
    神
    1.09
    løs
    1.08
    bộ
    1.07
    Activations Density 0.017%

    No Known Activations