© 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. 90134
    Prev
    Next
    INDEX
    Explanations

    minimum wage

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

    The main thing this neuron does is detect mentions of minimum‐wage or wage‐related figures (e.g. “minimum,” “wage,” dollar amounts, and salary 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
    成績
    -0.88
     kari
    -0.78
    preferred
    -0.77
    략
    -0.77
    jos
    -0.73
     yol
    -0.72
    char
    -0.72
    sprintf
    -0.71
    TextSpan
    -0.71
    ristan
    -0.71
    POSITIVE LOGITS
     wage
    1.27
     Wage
    1.09
    FLOOR
    0.98
     legisl
    0.97
    Wage
    0.95
     earners
    0.95
    wage
    0.95
     wages
    0.94
     floor
    0.94
     Raising
    0.91
    Activations Density 0.013%

    No Known Activations