© 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. 40-GEMMASCOPE-2-RES-262K
    7. 24913
    Prev
    Next
    INDEX
    Explanations

    not just

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Very
    0.45
    Very
    0.42
     Doesn
    0.42
     Nerd
    0.42
    even
    0.41
     VERY
    0.40
     similarly
    0.40
    有
    0.40
     Practical
    0.39
     Even
    0.39
    POSITIVE LOGITS
    只是
    0.61
     necessarily
    0.59
     merely
    0.56
     necessariamente
    0.53
     necesariamente
    0.52
    necessarily
    0.49
    ただ
    0.46
    只不过
    0.45
    あくまで
    0.45
     फक्त
    0.42
    Activations Density 0.025%

    No Known Activations