© 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-65K
    7. 9490
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities in various languages

    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_65k_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
    各种
    0.54
     अक्सर
    0.52
    很多
    0.50
    各種
    0.48
     souvent
    0.47
    ıkları
    0.45
    ทั้ง
    0.45
    /*',
    0.44
     ብዙውን
    0.42
     |,
    0.42
    POSITIVE LOGITS
    0.48
     quatro
    0.43
     $
    0.43
    。
    0.43
     czter
    0.42
     vier
    0.42
     gemäß
    0.40
     tři
    0.40
     مبنی
    0.40
     zusätzlichen
    0.40
    Activations Density 0.133%

    No Known Activations