© 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. 116982
    Prev
    Next
    INDEX
    Explanations

    money amounts

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

    The neuron activates on numerals and monetary figures (digits, numbers, and dollar‐amount tokens).

    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
    nearly
    -1.06
    약
    -0.98
    almost
    -0.98
     prawie
    -0.96
     почти
    -0.96
     téměř
    -0.94
     presque
    -0.94
    approximately
    -0.86
    roughly
    -0.85
     casi
    -0.85
    POSITIVE LOGITS
     fifty
    1.15
    Fifty
    0.81
    5
    0.79
     fifteen
    0.78
     stasiun
    0.77
    {}
    0.75
    cipitation
    0.75
     satunya
    0.74
     Fifty
    0.73
     Gesù
    0.73
    Activations Density 0.049%

    No Known Activations