© 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. 135236
    Prev
    Next
    INDEX
    Explanations

    completion or optional steps

    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
    Negative Logits
    탰
    0.55
    ාව
    0.50
    સી
    0.46
    case
    0.45
     আসলে
    0.45
    糸
    0.44
    trä
    0.44
    popupTheme
    0.44
     ursprünglich
    0.44
     بھول
    0.44
    POSITIVE LOGITS
     coloring
    0.57
     crispy
    0.52
     colorless
    0.47
     brown
    0.47
     {
    0.45
     dynasties
    0.45
     when
    0.45
     kingdoms
    0.44
     colouring
    0.44
     carving
    0.43
    Activations Density 0.003%

    No Known Activations