© 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. 116
    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
    asley
    0.88
    chlor
    0.87
    chter
    0.87
    es
    0.84
    eing
    0.84
     amerikan
    0.83
    ir
    0.83
    e
    0.83
     bitmap
    0.82
    পত
    0.82
    POSITIVE LOGITS
     definitively
    0.86
     書い
    0.86
    후
    0.81
    ли
    0.80
    scripts
    0.79
     confidently
    0.75
    там
    0.75
     दिलों
    0.74
    ту
    0.72
     Пи
    0.71
    Activations Density 0.000%

    No Known Activations