© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208023
    Prev
    Next
    INDEX
    Explanations

    medical or mental health

    np_acts-logits-general · gemini-2.5-flash-lite

    science, math, and non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     spraying
    0.50
     disinfectant
    0.48
     splitting
    0.48
    挠
    0.47
     Lup
    0.47
    다가
    0.46
     stripping
    0.46
     little
    0.45
     shutdown
    0.44
     doping
    0.44
    POSITIVE LOGITS
    Ⴖ
    0.55
    诅
    0.53
     मॉल
    0.48
    腃
    0.48
    রের
    0.48
    പോ
    0.48
     تعلمنا
    0.48
    ഏ
    0.48
    šnj
    0.47
    Zs
    0.47
    Activations Density 0.001%

    No Known Activations