© 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. 151906
    Prev
    Next
    INDEX
    Explanations

    options, true, regulations, sacred, last, redundancy

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

    streaming, encryption, websites, performance

    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
    afio
    0.50
     সি
    0.48
    Disha
    0.48
    🏪
    0.48
    ্সি
    0.47
    łuż
    0.47
    的产品
    0.47
    nje
    0.46
    prz
    0.46
    пуск
    0.46
    POSITIVE LOGITS
     degeneration
    0.54
     retrie
    0.53
     website
    0.50
     degeneracy
    0.50
     Budget
    0.50
     to
    0.49
     Retrieved
    0.49
    </h2>
    0.49
     Website
    0.48
     bandwidth
    0.48
    Activations Density 0.001%

    No Known Activations