© 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. 16-GEMMASCOPE-2-RES-262K
    7. 35886
    Prev
    Next
    INDEX
    Explanations

    code structure and problems

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     tudo
    0.58
    Linux
    0.57
     sepsis
    0.56
     बहुत
    0.54
     Linux
    0.54
    ipada
    0.54
     groot
    0.53
    AT
    0.53
     sangu
    0.53
     b
    0.52
    POSITIVE LOGITS
    享有
    0.52
     acclaimed
    0.50
     മാത്ര
    0.50
     Situated
    0.49
     שני
    0.48
     مالی
    0.47
     नज़र
    0.47
    িসি
    0.47
     एक्सेस
    0.46
     डिल
    0.46
    Activations Density 0.048%

    No Known Activations