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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12434
    Prev
    Next
    INDEX
    Explanations

    Data, China, AI, economy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_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
    pendiente
    0.43
     एखा
    0.42
     خير
    0.40
    inian
    0.39
    歹
    0.39
    粈
    0.39
    榻
    0.39
     الحلقه
    0.38
    齟
    0.37
    钚
    0.37
    POSITIVE LOGITS
     ber
    0.43
     billions
    0.41
     "
    0.39
     financial
    0.38
          
    0.37
     matters
    0.37
    #"
    0.37
     crammed
    0.37
     agreed
    0.36
    "
    0.36
    Activations Density 0.027%

    No Known Activations