© 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. 531
    Prev
    Next
    INDEX
    Explanations

    Kuala Lumpur

    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_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
     and
    0.56
     if
    0.54
    0.53
    ९
    0.49
     or
    0.47
     flowchart
    0.46
     for
    0.46
     includes
    0.45
    পাতা
    0.45
    ኪያ
    0.45
    POSITIVE LOGITS
    ,
    0.62
    .
    0.57
     města
    0.54
    Fun
    0.51
     Belediyesi
    0.50
    дин
    0.49
    ?
    0.49
    ა
    0.48
    大
    0.48
    బాద్
    0.48
    Activations Density 2.490%

    No Known Activations