© 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. 16-GEMMASCOPE-2-RES-262K
    7. 90407
    Prev
    Next
    INDEX
    Explanations

    Fortran programs and language

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ка
    0.63
    ோ
    0.61
     друзья
    0.59
    вого
    0.58
     внутренней
    0.57
    2
    0.57
    ↵
    0.56
    6
    0.56
     AliExpress
    0.55
         
    0.55
    POSITIVE LOGITS
     franch
    0.64
     speckled
    0.64
     it
    0.62
     urin
    0.58
    ussie
    0.57
     ling
    0.57
     aument
    0.56
     prenn
    0.56
     treads
    0.56
     ene
    0.55
    Activations Density 0.001%

    No Known Activations