© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12738
    Prev
    Next
    INDEX
    Explanations

    Britain and Ireland

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

    schedule or tasks

    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
    Not in Any Lists

    No Comments

    Negative Logits
    0.36
      
    0.35
     the
    0.34
     an
    0.34
     main
    0.34
     over
    0.34
     a
    0.33
     in
    0.33
     to
    0.33
     end
    0.33
    POSITIVE LOGITS
    玖章
    0.35
     नाइट्रेट
    0.35
     रिलेट
    0.34
     Luật
    0.33
     دهد
    0.32
     क्लोरीन
    0.32
     clínicos
    0.32
     produktów
    0.32
     Tổ
    0.32
     elektromagnet
    0.32
    Activations Density 0.000%

    No Known Activations