© 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-65K
    7. 3579
    Prev
    Next
    INDEX
    Explanations

    what kind of

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    1.06
     a
    0.90
     (
    0.75
    you
    0.73
    nX
    0.73
     முதல்
    0.72
    ，
    0.70
    k
    0.69
    kta
    0.69
    enario
    0.68
    POSITIVE LOGITS
     and
    1.22
    و
    1.20
    на
    1.18
    ik
    1.16
    ل
    1.15
    ق
    1.13
    and
    1.04
     can
    1.02
    1
    1.00
    י
    0.99
    Activations Density 0.560%

    No Known Activations