© 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. 31-GEMMASCOPE-2-RES-65K
    7. 44884
    Prev
    Next
    INDEX
    Explanations

    end of comment block

    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_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ئة
    0.40
     Connell
    0.38
     hydrocarbons
    0.38
     脚
    0.38
     kennel
    0.37
     resented
    0.37
    rowned
    0.37
     Mercier
    0.37
    ondale
    0.37
    occan
    0.36
    POSITIVE LOGITS
     ಅದನ್ನು
    0.45
     maxValue
    0.42
    能夠
    0.42
    那你
    0.41
     दिए
    0.41
    好的
    0.40
     Turing
    0.40
    能
    0.39
    敂
    0.39
    能够
    0.38
    Activations Density 0.002%

    No Known Activations