© 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. 170708
    Prev
    Next
    INDEX
    Explanations

    pursuing innovation, enjoying variety

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

    moisturizing, confidence, history, nutrition

    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
     merda
    0.54
     Kxc
    0.52
     kalau
    0.52
     Shimizu
    0.51
     가서
    0.51
     이거
    0.50
     אבל
    0.48
    嘛
    0.48
    的時候
    0.48
     mesela
    0.47
    POSITIVE LOGITS
    丰富的
    0.55
    checkFor
    0.51
    மிகு
    0.49
    さまざまな
    0.48
     awaits
    0.48
    กับการ
    0.47
    様々な
    0.47
    怀
    0.47
     tightly
    0.46
    を楽しむ
    0.46
    Activations Density 0.027%

    No Known Activations