© 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. 32948
    Prev
    Next
    INDEX
    Explanations

    product codes

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

    The neuron primarily activates on numerical tokens (e.g. years, figures, percentages, and other digit sequences).

    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
     Frühjahr
    -0.78
     might
    -0.75
     ఒ
    -0.73
     து
    -0.72
     局
    -0.72
    Răsp
    -0.70
     联
    -0.69
     beeintr
    -0.67
     Verfü
    -0.67
     cư
    -0.66
    POSITIVE LOGITS
     Frost
    1.06
    Frost
    0.99
    ADAS
    0.91
    נ
    0.90
    Revenue
    0.89
    İL
    0.89
     revenue
    0.88
    ţie
    0.87
     forecasts
    0.87
    Segmentation
    0.85
    Activations Density 0.014%

    No Known Activations