© 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. 46629
    Prev
    Next
    INDEX
    Explanations

    connection, value, level, name, answer, repetition

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

    multilingual concepts and examples

    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
     बतौर
    0.60
     steeple
    0.49
    ዔ
    0.49
     แถม
    0.48
    बताया
    0.47
    ्रेंस
    0.46
    ड़ी
    0.45
     ทั้ง
    0.45
     อาท
    0.44
    clair
    0.44
    POSITIVE LOGITS
    または
    0.65
     öğ
    0.62
    奇怪
    0.62
    ：
    0.59
     మరియు
    0.59
    旨在
    0.59
     ​​
    0.58
    および
    0.57
     için
    0.54
    的所有
    0.54
    Activations Density 0.012%

    No Known Activations