© 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. 13580
    Prev
    Next
    INDEX
    Explanations

    custom log format python 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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     المصفوفه
    0.46
    serr
    0.39
    ві
    0.39
     মুজিবর
    0.39
    னால
    0.39
    є
    0.38
     atypical
    0.38
     participante
    0.38
     کمار
    0.38
    ্ধ্য
    0.37
    POSITIVE LOGITS
    Bodies
    0.38
    几年
    0.37
    toh
    0.37
    Traits
    0.37
    >>;
    0.36
     brewing
    0.36
    ToObject
    0.35
    ToStr
    0.35
     Recycling
    0.35
    钙
    0.35
    Activations Density 0.002%

    No Known Activations