© 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-16K
    7. 6624
    Prev
    Next
    INDEX
    Explanations

    comparing people just above and below

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cup
    0.46
     Право
    0.44
    #
    0.44
     sm
    0.44
     cups
    0.43
    .
    0.42
    Updated
    0.42
     faire
    0.41
    lors
    0.41
     from
    0.40
    POSITIVE LOGITS
    ướ
    0.40
    flashlight
    0.38
    侵害
    0.38
     Islamist
    0.37
    ងារ
    0.37
    麾
    0.37
     வளர்ச்சி
    0.37
     prosecutions
    0.37
    𝗄
    0.37
     वगैर
    0.36
    Activations Density 0.007%

    No Known Activations