© 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. 116902
    Prev
    Next
    INDEX
    Explanations

    begins Monday

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

    many foreign languages

    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
     incorporates
    0.54
    ف
    0.51
     with
    0.47
    囩
    0.47
    for
    0.46
     endeavors
    0.45
     renversement
    0.45
    ing
    0.44
    ik
    0.43
    شم
    0.43
    POSITIVE LOGITS
     असंभव
    0.50
     Многие
    0.48
     প্রতির
    0.47
     മനുഷ്യ
    0.47
     कैंसर
    0.47
     баста
    0.46
     ঘনিষ্ঠ
    0.45
    滌
    0.45
     특히
    0.45
     приготов
    0.45
    Activations Density 0.000%

    No Known Activations