© 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. 210242
    Prev
    Next
    INDEX
    Explanations

    simple instances, complex cases

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

    explaining complex concepts simply

    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
     recib
    0.55
     cír
    0.50
     jef
    0.48
    贵
    0.48
     roy
    0.47
    haz
    0.47
    يلات
    0.46
     příjem
    0.46
     recicl
    0.46
     aniversario
    0.46
    POSITIVE LOGITS
    simpleType
    0.53
    ishly
    0.50
     단순히
    0.49
    መ
    0.48
     जटिल
    0.48
     স্থল
    0.47
     단순
    0.46
     ಸಾಧ್ಯ
    0.46
     ಪ್ರಕರಣ
    0.46
    ске
    0.45
    Activations Density 0.000%

    No Known Activations