© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115778
    Prev
    Next
    INDEX
    Explanations

    benefit risk cost

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

    The neuron activates on numeric and quantitative terms—numbers, percentages, and metric words like “risk,” “cost,” “benefit,” and “ratio.”

    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
    気が
    -0.88
    othermal
    -0.84
    ₁(
    -0.82
     geladen
    -0.80
    tructuring
    -0.80
    prehensive
    -0.79
    umumkan
    -0.78
    truct
    -0.77
    ELAND
    -0.75
     siè
    -0.75
    POSITIVE LOGITS
     benefits
    3.94
     benefit
    3.84
     Benefits
    3.17
     Benefit
    3.09
    Benefit
    3.08
    benefit
    3.03
    benefits
    2.95
    Benefits
    2.81
     risk
    2.56
     BENEFITS
    2.30
    Activations Density 0.066%

    No Known Activations