© 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. 484
    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
     bluntly
    0.92
    ’
    0.92
     хоть
    0.91
    Ϊ
    0.90
    ngày
    0.87
     якобы
    0.86
     里
    0.84
    രിയായ
    0.84
    льга
    0.82
    lardır
    0.80
    POSITIVE LOGITS
     flasks
    1.08
    𝘴
    0.92
     bikes
    0.92
     motorcycles
    0.92
     biker
    0.87
     potions
    0.86
    ز
    0.86
     fittings
    0.85
     motorcycl
    0.84
     tubes
    0.84
    Activations Density 0.000%

    No Known Activations