© 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. 35737
    Prev
    Next
    INDEX
    Explanations

    bill of rights

    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
    ു
    0.63
     meshes
    0.55
     mucus
    0.55
     germs
    0.55
     masts
    0.54
     syringes
    0.54
     flicks
    0.53
     multitudes
    0.52
     ત્રણ
    0.52
    educ
    0.51
    POSITIVE LOGITS
     Continuando
    0.59
     Harus
    0.56
    (",")
    0.55
    [,
    0.55
    홈
    0.54
    ()
    0.54
    "),
    0.54
    ").
    0.54
    [(
    0.54
     Уи
    0.54
    Activations Density 0.003%

    No Known Activations