© 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. 164993
    Prev
    Next
    INDEX
    Explanations

    contestants and performance times

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

    design, control, project, Decoration

    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
     เงี้ย
    0.47
     단순
    0.47
     Acme
    0.45
     OpenAI
    0.44
    kyl
    0.44
    ష్
    0.43
    ೋಗ್ಯ
    0.43
    𝐊
    0.43
     없이
    0.43
     쓰는
    0.43
    POSITIVE LOGITS
    Furniture
    0.50
    ¿
    0.46
    Diagnostic
    0.46
    decorator
    0.44
    Decoration
    0.43
     আস্তে
    0.43
    2
    0.42
    CallBack
    0.42
     Revenue
    0.41
     ¿
    0.41
    Activations Density 0.003%

    No Known Activations