© 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. 73327
    Prev
    Next
    INDEX
    Explanations

    low levels or below

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

    The neuron strongly activates on words naming quantitative measures and statistical indicators—e.g. rates, levels, declines—that introduce or accompany numeric data.

    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
    increase
    -1.30
     supérieure
    -1.29
     superiore
    -1.15
     større
    -1.09
     supérieures
    -1.09
    larger
    -1.07
     превы
    -1.06
     upstairs
    -1.05
    increases
    -1.05
    大于
    -1.03
    POSITIVE LOGITS
     low
    4.03
     lower
    3.69
     below
    3.55
     lowest
    3.16
    低
    2.89
     LOW
    2.77
    ต่
    2.73
     ниже
    2.70
    低于
    2.69
    Low
    2.66
    Activations Density 0.347%

    No Known Activations