© 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. 30188
    Prev
    Next
    INDEX
    Explanations

    non-english texts

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

    briefly describe specific details

    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
    t
    0.52
     to
    0.45
     tempt
    0.45
    ;
    0.45
     rì
    0.44
    도
    0.44
     makers
    0.44
     virkelig
    0.44
     traveller
    0.43
     semp
    0.43
    POSITIVE LOGITS
     јо
    0.57
     начну
    0.54
     производство
    0.52
     pInBuffer
    0.52
     それぞれ
    0.52
     аудио
    0.51
     Нужно
    0.48
     によって
    0.48
     பிரபலமான
    0.47
    垃
    0.47
    Activations Density 0.000%

    No Known Activations