© 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. 84055
    Prev
    Next
    INDEX
    Explanations

    economies of scale

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

    The neuron detects promotional or marketing‐style language—superlatives and pitchy descriptors common in corporate or financial PR copy.

    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
    tikz
    -0.85
    ösungen
    -0.82
    ядок
    -0.81
     stipend
    -0.80
    ouan
    -0.78
    icit
    -0.76
    beyaz
    -0.75
    ntä
    -0.75
     metamorphosis
    -0.75
     daggers
    -0.75
    POSITIVE LOGITS
     economies
    2.52
     scale
    2.47
    scale
    2.09
     efficiencies
    1.84
    Scale
    1.83
     Scale
    1.69
    规模
    1.68
     escala
    1.62
     масшта
    1.56
     Economies
    1.56
    Activations Density 0.023%

    No Known Activations