© 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. 44626
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
     Manuscripts
    0.46
    :=
    0.40
     Crab
    0.40
    ว่าจะ
    0.39
    总之
    0.39
    Only
    0.37
     bowiem
    0.37
    ៕
    0.37
     =>
    0.37
     Supplementary
    0.37
    POSITIVE LOGITS
    請問
    0.80
     هل
    0.75
     Apakah
    0.62
     Why
    0.59
     What
    0.57
     ¿
    0.57
     શું
    0.57
     Какие
    0.57
     কেমন
    0.56
    Why
    0.55
    Activations Density 0.268%

    No Known Activations