© 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. 172618
    Prev
    Next
    INDEX
    Explanations

    Ninja Turtles

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

    code status checks

    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
    т
    0.53
     t
    0.52
    ت
    0.50
     Lur
    0.49
     Westfield
    0.49
     sur
    0.48
     Gillette
    0.48
    صد
    0.48
     push
    0.47
    stes
    0.46
    POSITIVE LOGITS
     谢
    0.54
     系统
    0.49
     开发
    0.47
     პრო
    0.46
     พา
    0.46
    StarGo
    0.45
     装
    0.44
     土
    0.44
    LuaPush
    0.44
     没有
    0.44
    Activations Density 0.000%

    No Known Activations