© 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. 56882
    Prev
    Next
    INDEX
    Explanations

    Baby and department categories

    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
    Not in Any Lists

    No Comments

    Negative Logits
    வார்
    0.42
    гин
    0.40
    ⁡
    0.39
     fortified
    0.38
    rát
    0.38
    Truly
    0.37
    рная
    0.37
     Plut
    0.36
    倏
    0.36
     памят
    0.36
    POSITIVE LOGITS
    department
    0.47
     بچہ
    0.45
     অপরিচিত
    0.40
    CXX
    0.40
    fashion
    0.38
     department
    0.38
    industrial
    0.38
     फैशन
    0.38
    豬
    0.38
    壓縮
    0.37
    Activations Density 0.001%

    No Known Activations