© 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. 107382
    Prev
    Next
    INDEX
    Explanations

    full node

    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
     어린이
    0.81
    드를
    0.73
     가
    0.72
    는
    0.71
     говорят
    0.70
     바람
    0.70
     microtubules
    0.70
     basilica
    0.67
     Bartholom
    0.67
     카드
    0.66
    POSITIVE LOGITS
    k
    1.18
    c
    1.05
    g
    0.97
    f
    0.97
    n
    0.96
    b
    0.89
    r
    0.89
    il
    0.88
    u
    0.84
    in
    0.82
    Activations Density 0.002%

    No Known Activations