© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6322
    Prev
    Next
    INDEX
    Explanations

    contrast or continuation conjunctions

    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
     নয়
    0.34
     jonka
    0.29
    यह
    0.27
    રે
    0.27
     येईल
    0.26
    Pepper
    0.26
    ಬ
    0.26
    बे
    0.26
     joka
    0.26
    plemented
    0.26
    POSITIVE LOGITS
     but
    0.37
     nhưng
    0.36
     amd
    0.35
     ប៉ុ
    0.35
     although
    0.33
     despite
    0.33
     unless
    0.32
     لكن
    0.32
     before
    0.32
     whence
    0.32
    Activations Density 0.088%

    No Known Activations