© 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-65K
    7. 56598
    Prev
    Next
    INDEX
    Explanations

    concepts and descriptions

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     powierzchn
    0.42
    itement
    0.41
     scène
    0.40
     سكس
    0.40
    uidas
    0.40
     поверхность
    0.40
    ственное
    0.39
     آیا
    0.39
     ([
    0.39
     Pensions
    0.39
    POSITIVE LOGITS
    ERT
    0.44
    ab
    0.42
    <\
    0.41
    SOs
    0.40
     healthier
    0.39
    Hasta
    0.39
    Gior
    0.39
    Carr
    0.38
    eris
    0.38
    ER
    0.38
    Activations Density 0.000%

    No Known Activations