© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15363
    Prev
    Next
    INDEX
    Explanations

    quantifying large amounts

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

    large quantities expressed numerically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     approximately
    0.70
     four
    0.55
     estrogen
    0.54
     two
    0.54
     was
    0.52
     noin
    0.52
     and
    0.52
     "@
    0.51
     indique
    0.51
     è
    0.50
    POSITIVE LOGITS
     thousands
    1.23
    Thousands
    1.22
    thousands
    1.22
    数百
    1.20
     Hundreds
    1.19
    Hundreds
    1.18
     hundreds
    1.16
     हजारों
    1.16
     milhares
    1.15
     decenas
    1.15
    Activations Density 0.147%

    No Known Activations