© 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. 230
    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
    ó
    0.78
    ع
    0.63
     vết
    0.62
     Leung
    0.62
    ر
    0.61
     honorable
    0.60
    م
    0.60
    ق
    0.60
    hare
    0.59
     cordial
    0.59
    POSITIVE LOGITS
     amores
    0.63
    િંગ
    0.63
    ій
    0.59
     conjunta
    0.55
    쩜
    0.54
    帙
    0.54
    iverse
    0.53
    鍘
    0.53
    比亚
    0.53
     Colombeau
    0.52
    Activations Density 6.759%

    No Known Activations