© 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-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 402
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    з
    1.22
     ώστε
    1.15
    なかなか
    1.09
    ع
    1.09
    إذا
    1.09
    ત
    1.07
    ر
    1.06
    การ
    1.05
    с
    1.04
    你
    1.02
    POSITIVE LOGITS
    romeda
    1.06
    ंगाबाद
    1.02
     whatnot
    0.90
    ri
    0.89
    ser
    0.88
     secondly
    0.88
    ne
    0.87
    rogens
    0.86
     sebagainya
    0.85
    irons
    0.84
    Activations Density 2.846%

    No Known Activations