© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21837
    Prev
    Next
    INDEX
    Explanations

    scientific instruments, long periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     two
    0.48
     all
    0.47
     oper
    0.46
     but
    0.46
     r
    0.44
    }$,
    0.43
    ли
    0.43
    বা
    0.42
     bacterial
    0.41
    əs
    0.41
    POSITIVE LOGITS
    Productos
    0.47
     продуктов
    0.47
    atribut
    0.46
    categorias
    0.46
     кеңсеси
    0.45
    ficha
    0.44
    adol
    0.43
    Escolhido
    0.43
     принадле
    0.43
    ayad
    0.43
    Activations Density 0.000%

    No Known Activations