© 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. 217979
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases

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

    legal context or specific entities

    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
    лет
    0.50
    叓
    0.50
    и
    0.50
    тим
    0.49
    یم
    0.49
     gouvernement
    0.48
    掫
    0.48
    ми
    0.48
     дет
    0.48
     توهان
    0.48
    POSITIVE LOGITS
     Capita
    0.48
     Gui
    0.46
     Damian
    0.45
    Tourism
    0.45
    Dai
    0.44
     colloqu
    0.43
     Guerr
    0.43
     Fabi
    0.43
    War
    0.43
    ,[
    0.43
    Activations Density 0.001%

    No Known Activations