© 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. 173930
    Prev
    Next
    INDEX
    Explanations

    intercultural foreign language education

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

    decisions and discussions

    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
    ניין
    0.51
    ЛА
    0.50
    DE
    0.48
    LAS
    0.47
    薩
    0.46
    龰
    0.46
    LA
    0.46
    VA
    0.46
     दाब
    0.46
     JAS
    0.46
    POSITIVE LOGITS
     uh
    0.50
     ethically
    0.49
     Gren
    0.47
     morally
    0.46
     electrically
    0.45
     solidar
    0.45
    Gre
    0.44
     insolvent
    0.44
    Gren
    0.43
     &
    0.43
    Activations Density 0.001%

    No Known Activations