© 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. 108103
    Prev
    Next
    INDEX
    Explanations

    combination of items or concepts

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

    rare, eye, test, rendered, premium, navigating, dreams

    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
    ա
    0.47
    。「
    0.45
    ৬
    0.45
     allemaal
    0.45
    ể
    0.44
     Université
    0.44
    一个个
    0.44
    ంగా
    0.43
     SIST
    0.43
     Universidade
    0.43
    POSITIVE LOGITS
     انہ
    0.50
     फ्रै
    0.46
     مسئلہ
    0.44
     زمانہ
    0.44
     porosity
    0.44
     کردی
    0.43
    கூ
    0.43
    𝚍
    0.43
    cake
    0.42
     ملک
    0.42
    Activations Density 0.001%

    No Known Activations