© 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. 205841
    Prev
    Next
    INDEX
    Explanations

    Python BscScan scripts

    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
     utilisent
    0.54
    מ
    0.51
    ม
    0.50
     грузо
    0.49
     skirting
    0.49
    私たちは
    0.47
     vortices
    0.46
     skirts
    0.46
     worrisome
    0.46
     naszym
    0.46
    POSITIVE LOGITS
    dag
    0.48
    HL
    0.47
    عدة
    0.45
    Tb
    0.44
    نوات
    0.43
    Bb
    0.43
    Brom
    0.43
    4
    0.43
    лює
    0.41
    BB
    0.41
    Activations Density 0.004%

    No Known Activations