© 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. 40-GEMMASCOPE-2-RES-16K
    7. 7731
    Prev
    Next
    INDEX
    Explanations

    processes occurring

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     업무
    0.42
     реаль
    0.40
     찾는
    0.39
     وار
    0.39
     함
    0.38
     оправ
    0.38
    脨
    0.38
    が登場
    0.38
    녜
    0.37
    ارع
    0.37
    POSITIVE LOGITS
     occurring
    0.82
     occuring
    0.81
     rates
    0.79
     rate
    0.71
     occur
    0.71
     occurs
    0.69
     happening
    0.68
    率
    0.68
    rates
    0.65
    rate
    0.64
    Activations Density 0.169%

    No Known Activations