© 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. 1214
    Prev
    Next
    INDEX
    Explanations

    how what why

    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
     Φ
    0.38
     Helix
    0.36
     shelling
    0.36
     sondern
    0.36
     بدون
    0.36
     পী
    0.35
     Tart
    0.35
     Λ
    0.35
     stallion
    0.35
     Chopin
    0.35
    POSITIVE LOGITS
     how
    1.36
     what
    1.14
     cómo
    1.08
    how
    1.05
     bagaimana
    1.05
     hvordan
    1.04
     why
    1.01
    what
    0.99
     কিভাবে
    0.97
    如何
    0.96
    Activations Density 0.270%

    No Known Activations