© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90910
    Prev
    Next
    INDEX
    Explanations

    finish the meal

    np_acts-logits-general · gemini-2.5-flash-lite

    before releasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    /
    0.50
    可谓
    0.50
    ،
    0.48
    ا
    0.47
    实在是
    0.45
     muchísimo
    0.45
    ..
    0.45
    اي
    0.45
    =
    0.45
     qua
    0.44
    POSITIVE LOGITS
    codone
    0.46
    کروچ
    0.46
     বসব
    0.45
     इमरजेंसी
    0.44
     Cristiano
    0.43
     ਉਨ੍ਹਾਂ
    0.43
     రెండో
    0.43
    ds
    0.43
    crc
    0.43
    ollary
    0.43
    Activations Density 0.001%

    No Known Activations