© 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. 4751
    Prev
    Next
    INDEX
    Explanations

    closing script tag

    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
    Negative Logits
    ಿದರೆ
    0.55
    음
    0.54
    ιν
    0.51
     Prizes
    0.50
    위에
    0.50
    िंग
    0.49
    ための
    0.49
     hardwoods
    0.49
     pequenas
    0.49
    ին
    0.48
    POSITIVE LOGITS
    S
    0.74
     jacket
    0.55
    ited
    0.54
     de
    0.52
     S
    0.51
     commander
    0.51
     韩
    0.50
     backed
    0.50
     书
    0.50
     knight
    0.49
    Activations Density 0.002%

    No Known Activations