© 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-262K
    7. 1243
    Prev
    Next
    INDEX
    Explanations

    Choose, solve, select, list

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     brainchild
    0.31
    жий
    0.30
    écie
    0.28
    貓
    0.28
    འི་
    0.27
     comércio
    0.27
    ご飯
    0.27
     своё
    0.27
    핞
    0.26
    もし
    0.25
    POSITIVE LOGITS
     Thinking
    0.37
     Which
    0.33
     Comb
    0.31
     thinking
    0.29
     Sketch
    0.29
     Help
    0.29
     Ком
    0.29
     Examples
    0.29
     Slides
    0.29
    Thinking
    0.28
    Activations Density 0.001%

    No Known Activations