© 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. 20414
    Prev
    Next
    INDEX
    Explanations

    English and foreign phrases

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

    competition, presence, trials

    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
    ð
    0.42
    agi
    0.41
    但也
    0.39
    NG
    0.39
    但在
    0.39
     dibagi
    0.39
    ł
    0.38
     आर्थिक
    0.38
    ក៏
    0.38
    Н
    0.38
    POSITIVE LOGITS
     Sehingga
    0.48
    だったので
    0.46
     zodat
    0.46
     sehingga
    0.45
     arba
    0.45
    秘书
    0.45
    懒
    0.44
     eloku
    0.44
     Glossary
    0.44
    缬
    0.43
    Activations Density 0.000%

    No Known Activations