© 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. 85863
    Prev
    Next
    INDEX
    Explanations

    non-latin scripts

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

    inherent opposition or criticism

    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
     {:?}",
    0.48
    ಡುವುದ
    0.46
     Excellency
    0.45
     recuperar
    0.44
     lanzar
    0.43
     inputted
    0.43
     damning
    0.43
     irgende
    0.43
    ことなく
    0.43
    מד
    0.42
    POSITIVE LOGITS
    ک
    0.46
    Sha
    0.45
     শাহ
    0.45
    By
    0.45
    Ша
    0.45
    علی
    0.44
    سل
    0.44
     বে
    0.44
    歷史
    0.44
    ایک
    0.44
    Activations Density 0.001%

    No Known Activations