© 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. 41-GEMMASCOPE-2-RES-262K
    7. 21471
    Prev
    Next
    INDEX
    Explanations

    advantages add

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    หมือน
    0.69
    .³
    0.66
    .
    0.66
     देम
    0.65
    .​​
    0.64
    ็บ
    0.62
    ามารถ
    0.61
    routingHeader
    0.60
    .•
    0.60
     മിക
    0.59
    POSITIVE LOGITS
    in
    0.80
    1
    0.77
     It
    0.69
     What
    0.64
     The
    0.64
     In
    0.63
      
    0.62
    0
    0.61
     Unit
    0.60
     Social
    0.59
    Activations Density 0.013%

    No Known Activations