© 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. 74815
    Prev
    Next
    INDEX
    Explanations

    competitive pricing

    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
    чним
    0.57
    驄
    0.55
    kfollowers
    0.54
    Enqueue
    0.52
     പങ്കെടു
    0.50
    
    0.50
    ٹس
    0.49
    middels
    0.48
     enqueue
    0.48
     அலெ
    0.48
    POSITIVE LOGITS
     Affairs
    0.50
     \
    0.50
     Post
    0.47
     V
    0.46
     are
    0.44
     Disease
    0.43
     Safety
    0.43
     Shrine
    0.42
     First
    0.41
     Breast
    0.41
    Activations Density 0.001%

    No Known Activations