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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 4026
    Prev
    Next
    INDEX
    Explanations

    multi-lingual script origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sa
    1.00
    ting
    0.99
     tind
    0.98
     fie
    0.94
     l
    0.94
     ly
    0.92
     tient
    0.90
    sa
    0.89
     cea
    0.89
     sunt
    0.89
    POSITIVE LOGITS
    ‌ها
    1.43
     دیگر
    1.39
     برای
    1.38
     از
    1.38
     این
    1.36
     پ
    1.33
     در
    1.33
    ک
    1.32
     حتی
    1.32
     به
    1.30
    Activations Density 0.002%

    No Known Activations