© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95727
    Prev
    Next
    INDEX
    Explanations

    costs and expenses

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

    The neuron fires on numeric expressions—digits and numeral tokens that denote quantities or costs.

    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
    витие
    -1.02
    mgren
    -0.96
     worden
    -0.95
     distritos
    -0.94
    ността
    -0.93
    ꪔ
    -0.93
     dati
    -0.93
     cantar
    -0.92
     σημαν
    -0.92
    AZINE
    -0.91
    POSITIVE LOGITS
     costs
    2.13
    costs
    1.41
     cost
    1.38
     expenses
    1.35
     expensive
    1.34
     costly
    1.20
    ต้อง
    1.16
     هزینه
    1.16
    Costs
    1.16
     required
    1.15
    Activations Density 0.026%

    No Known Activations