© 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-262K
    7. 128936
    Prev
    Next
    INDEX
    Explanations

    code context with numbers

    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_262k_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
    稒
    0.55
    <unused2188>
    0.54
     പ്രശ്
    0.51
     توانید
    0.51
    ωσε
    0.51
    ATEG
    0.50
     म्हणजेच
    0.50
     previewBuilder
    0.50
    するため
    0.49
    )][
    0.49
    POSITIVE LOGITS
     of
    0.51
    -
    0.51
     greens
    0.49
     mains
    0.48
     in
    0.47
     použív
    0.47
     unconventional
    0.46
     is
    0.45
     black
    0.44
     live
    0.44
    Activations Density 0.002%

    No Known Activations