© 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. 34-GEMMASCOPE-RES-131K
    7. 111058
    Prev
    Next
    INDEX
    Explanations

    salary and compensation

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

    The neuron triggers on numeric values associated with pay or salary figures.

    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
     Fees
    -0.86
     метра
    -0.82
    ிர
    -0.81
     profonde
    -0.79
    :`
    -0.78
     Fee
    -0.77
    所需的
    -0.75
    measurable
    -0.74
    もう一度
    -0.74
     dirige
    -0.73
    POSITIVE LOGITS
     structure
    1.35
     scale
    1.27
     scales
    1.22
    SCALE
    1.12
    scale
    1.11
    结构
    1.10
     packages
    1.07
    Scale
    1.07
     expectations
    1.05
     structures
    0.99
    Activations Density 0.012%

    No Known Activations