© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5251
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    想
    0.77
    並且
    0.73
    凡
    0.73
    再來
    0.71
    ки
    0.71
     ایمان
    0.69
     ملاقات
    0.67
    僅
    0.67
    ﻤ
    0.67
    以及
    0.66
    POSITIVE LOGITS
     pixel
    0.94
     rRNA
    0.85
     radiative
    0.84
     pixels
    0.83
     RMSE
    0.82
     cardigan
    0.80
     nugget
    0.80
     superheroes
    0.80
     rebuild
    0.79
     rnorm
    0.78
    Activations Density 0.001%

    No Known Activations