© 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. 41-GEMMASCOPE-2-RES-65K
    7. 14673
    Prev
    Next
    INDEX
    Explanations

    recovery

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    岌
    0.61
     watering
    0.57
     ক্ষতিগ্রস্ত
    0.57
    上位
    0.57
     등장
    0.56
     heightened
    0.55
     kuts
    0.55
     повышен
    0.54
     dificuldade
    0.54
     تطوير
    0.54
    POSITIVE LOGITS
     cured
    1.34
    痊
    1.30
     cure
    1.22
     recoveries
    1.22
     recovery
    1.21
     completely
    1.20
     cures
    1.20
    完全
    1.17
     remission
    1.16
    completely
    1.16
    Activations Density 0.081%

    No Known Activations