© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1633
    Prev
    Next
    INDEX
    Explanations

    laws, regulations, and compliance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     rozm
    1.09
     ту
    1.00
    ях
    0.96
     برج
    0.91
    kę
    0.90
     دب
    0.90
    ❅
    0.88
    かし
    0.88
     संवाद
    0.88
    鐲
    0.87
    POSITIVE LOGITS
    规定的
    1.74
     regulations
    1.73
    规定
    1.68
     réglementation
    1.58
     allowable
    1.55
     normativa
    1.53
     Regulations
    1.53
     legalized
    1.47
    法规
    1.43
     legisl
    1.42
    Activations Density 0.798%

    No Known Activations