© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11358
    Prev
    Next
    INDEX
    Explanations

    multi-language content, blockchain, finance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hai
    0.61
     Vietnam
    0.52
     q
    0.52
     Vietnamese
    0.52
     Qin
    0.52
     Yun
    0.50
     Hai
    0.50
     phạm
    0.49
     ng
    0.49
     VN
    0.48
    POSITIVE LOGITS
     аўтаматы
    0.51
    ቝ
    0.50
    Liqu
    0.50
    ීර
    0.49
    Dropped
    0.49
    ‶
    0.49
    क्षित
    0.48
    總是
    0.48
    جاز
    0.48
    ੱਕ
    0.47
    Activations Density 0.035%

    No Known Activations