© 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. 178324
    Prev
    Next
    INDEX
    Explanations

    bulk domains

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

    ETFs and school

    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
     Archae
    0.49
    因此
    0.48
     Therefore
    0.44
    /
    0.43
     therefore
    0.43
     因此
    0.41
     spontaneously
    0.41
     {
    0.39
     anima
    0.39
     Researchers
    0.39
    POSITIVE LOGITS
    कू
    0.62
     উপযোগী
    0.57
    اکي
    0.57
    ўнай
    0.57
    ্সর
    0.56
    जम्मू
    0.53
    向けの
    0.52
    ufieurs
    0.52
     versie
    0.52
     yardımcı
    0.51
    Activations Density 0.000%

    No Known Activations