© 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. 84977
    Prev
    Next
    INDEX
    Explanations

    prices with currencies

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

    The neuron fires on numeric price values, i.e. dollar amounts or other monetary figures in the text.

    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
    ople
    -0.84
     stereotyp
    -0.69
    cipital
    -0.69
    यी
    -0.68
    ても
    -0.67
     benefiting
    -0.67
     Invisible
    -0.67
     troubles
    -0.65
     sức
    -0.65
     Imperial
    -0.65
    POSITIVE LOGITS
    9
    1.06
    ۹
    0.96
    十九
    0.93
    ৯
    0.91
    ۱۹
    0.87
     ninety
    0.82
    WILD
    0.82
    𝟗
    0.80
    Packages
    0.79
     ninjas
    0.79
    Activations Density 0.055%

    No Known Activations