© 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. 40-GEMMASCOPE-2-RES-65K
    7. 4511
    Prev
    Next
    INDEX
    Explanations

    words ending in -are or -ore

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    רט
    0.49
    رل
    0.45
    ລະ
    0.45
    IERC
    0.45
    룀
    0.45
    ر
    0.44
    ၻ
    0.44
    рита
    0.43
    分为
    0.43
    힣
    0.42
    POSITIVE LOGITS
    tta
    0.64
    nsics
    0.59
    ggere
    0.59
    gulation
    0.58
    lla
    0.56
    tti
    0.55
    gister
    0.55
    ño
    0.54
    cción
    0.54
    vo
    0.53
    Activations Density 0.063%

    No Known Activations