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. 12421
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     даже
    0.25
     покупать
    0.25
     финансо
    0.24
     soooo
    0.24
    लेकिन
    0.24
     laughable
    0.24
     प्रतिस्पर्
    0.23
     😏
    0.23
    লেও
    0.23
    해서
    0.23
    POSITIVE LOGITS
     are
    0.27
    '
    0.26
     water
    0.25
     is
    0.24
     may
    0.23
     provides
    0.22
     activities
    0.22
     were
    0.22
     began
    0.22
     processes
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.