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. 12441
    Prev
    Next
    INDEX
    Explanations

    descriptive evaluative terms

    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
    it
    0.73
    to
    0.70
    t
    0.68
    م
    0.66
    ب
    0.65
    tl
    0.61
    т
    0.61
    𝗧
    0.61
    c
    0.60
    et
    0.60
    POSITIVE LOGITS
     liberally
    0.58
     весьма
    0.54
    (?)
    0.52
     slipper
    0.52
     hefty
    0.51
     మూడు
    0.50
     tweaking
    0.50
     чи
    0.48
     ;-)
    0.48
     intrepid
    0.48
    Activations Density 0.441%

    No Known Activations