© 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. 7711
    Prev
    Next
    INDEX
    Explanations

    design, development, and engineering

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

    engineering and innovation

    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
    テーション
    0.54
    ন্যায়
    0.52
     социальной
    0.52
     peacefully
    0.51
    㕷
    0.50
     ಭಯ
    0.50
    ስቃ
    0.49
     Rajya
    0.49
    🤳
    0.49
     सांस्कृतिक
    0.48
    POSITIVE LOGITS
    研发
    1.25
     design
    1.24
     designing
    1.14
     engineering
    1.13
     разработки
    1.13
    设计
    1.12
     inventors
    1.12
     prototyping
    1.11
     designs
    1.09
     manufacturing
    1.09
    Activations Density 0.399%

    No Known Activations