© 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. 31609
    Prev
    Next
    INDEX
    Explanations

    software project structure

    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
     treba
    0.47
     divertido
    0.44
     aile
    0.44
     じゃん
    0.43
    ција
    0.42
    तुम्हारा
    0.41
    ก่
    0.40
     embaixo
    0.40
    Ž
    0.39
     אם
    0.39
    POSITIVE LOGITS
     Makefile
    0.45
    utils
    0.44
     Scanner
    0.41
     Selection
    0.40
     CUDA
    0.38
    Makefile
    0.38
     шриф
    0.38
     Circuit
    0.38
     Factory
    0.37
    ServiceImpl
    0.37
    Activations Density 0.098%

    No Known Activations