© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2969
    Prev
    Next
    INDEX
    Explanations

    which is

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    പ്പെ
    0.34
     +(
    0.34
    '
    0.34
    an
    0.31
     писа
    0.31
     చా
    0.31
     choisi
    0.30
     SBC
    0.29
     //</
    0.29
    +')
    0.29
    POSITIVE LOGITS
     means
    0.62
     wiederum
    0.55
    means
    0.53
     happens
    0.50
     isn
    0.49
    是一种
    0.49
     is
    0.48
     betekent
    0.48
     begs
    0.47
     complicates
    0.47
    Activations Density 0.012%

    No Known Activations