© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11010
    Prev
    Next
    INDEX
    Explanations

    numbers and their representations

    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_31_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
     transverse
    0.40
    சியா
    0.37
     క
    0.37
    ुकी
    0.37
    鈳
    0.36
     قابل
    0.36
     рассчита
    0.36
     ಬೇ
    0.36
     Vasil
    0.36
     बकाया
    0.36
    POSITIVE LOGITS
     five
    0.48
    5
    0.47
     cinque
    0.46
     premise
    0.42
    五
    0.42
    ۵
    0.41
    five
    0.41
     cinq
    0.40
     ஐந்து
    0.40
     quinqu
    0.39
    Activations Density 0.191%

    No Known Activations