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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 54
    Prev
    Next
    INDEX
    Explanations

    and / ; / & following words

    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
    ک
    0.55
    ».
    0.54
    .\
    0.52
    >>&
    0.52
     according
    0.51
    ﹒
    0.50
    تهای
    0.49
    ('').
    0.49
    [\
    0.49
    .
    0.49
    POSITIVE LOGITS
    يئة
    0.65
     તેના
    0.52
    टीन
    0.51
    Bub
    0.51
     તેની
    0.51
     исследова
    0.50
    சிக்க
    0.49
    تمر
    0.49
    PFA
    0.49
    ीट
    0.49
    Activations Density 0.002%

    No Known Activations