Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B
    3. 12-GEMMASCOPE-2-RES-16K
    4. 154
    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
    РА
    0.66
     и
    0.61
     और
    0.57
    RA
    0.56
     писать
    0.54
     отца
    0.54
    आई
    0.53
    ק
    0.53
     voltar
    0.52
     सॉरी
    0.52
    POSITIVE LOGITS
    ️⃣
    0.72
    ↵↵
    0.70
    ↵
    0.68
    ⃣
    0.57
    つの
    0.55
    おり
    0.54
    豊かな
    0.53
     রয়েছে
    0.48
    মূলক
    0.48
    ྔ
    0.48
    Activations Density 3.840%

    No Known Activations