© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15212
    Prev
    Next
    INDEX
    Explanations

    say "romanization"

    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
    亲自
    0.61
     ব্যান
    0.61
    笨
    0.58
    中年
    0.54
    ଲେ
    0.54
    ﹡
    0.52
    льні
    0.51
     जिनके
    0.51
     ویکی‌پدیا
    0.51
    记者
    0.50
    POSITIVE LOGITS
     :");
    0.61
     :
    0.59
     latency
    0.59
     AudioManager
    0.59
     Challenges
    0.56
     gaussian
    0.56
     desafio
    0.56
     düğ
    0.56
     Nodes
    0.55
     AVR
    0.55
    Activations Density 0.008%

    No Known Activations