© 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. 327
    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
     tâche
    0.88
    ंश
    0.82
    СР
    0.80
    OW
    0.79
     automate
    0.79
    PositionY
    0.78
    ocardial
    0.77
    疽
    0.77
    ット
    0.76
    बादी
    0.76
    POSITIVE LOGITS
     ткань
    0.97
     histó
    0.84
     mån
    0.83
    fü
    0.81
    ı
    0.75
    nál
    0.75
    нный
    0.74
     माधव
    0.74
    ní
    0.73
     клеток
    0.73
    Activations Density 0.000%

    No Known Activations