© 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. 424
    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
    ный
    0.88
    ם
    0.75
    ные
    0.73
    ')],
    0.72
    premises
    0.71
    ishw
    0.71
     получаем
    0.71
    ')])
    0.70
    այր
    0.70
    eneration
    0.70
    POSITIVE LOGITS
     răng
    0.89
    Terry
    0.77
    胰
    0.77
     Terry
    0.76
    Одна
    0.75
    젼
    0.75
     réunion
    0.75
     Barrington
    0.74
     Camille
    0.73
    Megan
    0.72
    Activations Density 0.000%

    No Known Activations