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
    3. 16-GEMMASCOPE-2-RES-16K
    4. 218
    Prev
    Next
    INDEX
    Explanations

    became a, delete the, fall of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_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
     ወይም
    0.66
     veya
    0.63
    :
    0.63
     ಅಥವಾ
    0.61
     atau
    0.60
     किंवा
    0.59
     eller
    0.56
     ਜਾਂ
    0.56
     nebo
    0.55
     หรือ
    0.54
    POSITIVE LOGITS
    ل
    0.57
    轺
    0.56
    fbox
    0.55
    你
    0.54
    雔
    0.52
    BeerItem
    0.52
     Ergebn
    0.52
    Asalamualaikum
    0.52
    咒
    0.52
    ı
    0.51
    Activations Density 0.003%

    No Known Activations