© 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. 116280
    Prev
    Next
    INDEX
    Explanations

    after-sales support

    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
    DE
    0.51
    CE
    0.50
    .
    0.49
    Raw
    0.48
    TE
    0.48
    VE
    0.48
    m
    0.47
    de
    0.47
     medic
    0.47
    (
    0.47
    POSITIVE LOGITS
     Abon
    0.53
     Constantinople
    0.51
     ![
    0.51
     Người
    0.50
     እየሱስ
    0.50
     Aspergillus
    0.50
     CuO
    0.50
    ukul
    0.49
    鹃
    0.49
     Erwach
    0.49
    Activations Density 0.000%

    No Known Activations