© 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. 41-GEMMASCOPE-2-RES-262K
    7. 98508
    Prev
    Next
    INDEX
    Explanations

    learning about specific topics

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Prosperity
    0.41
     consp
    0.40
    ως
    0.38
     contraction
    0.38
     anvä
    0.36
     prosperity
    0.36
    สนามกีฬา
    0.35
    contraction
    0.35
    祟
    0.35
    divisions
    0.34
    POSITIVE LOGITS
     dumped
    0.44
     Kurulu
    0.40
    0.39
    吏
    0.38
                  
    0.38
     नाइट्र
    0.38
     تشتغل
    0.37
     aspett
    0.37
     tez
    0.37
    쏜
    0.36
    Activations Density 1.115%

    No Known Activations