© 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. 51170
    Prev
    Next
    INDEX
    Explanations

    request a showing

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

    delayed request handling

    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
    遌
    0.48
    れています
    0.46
     теат
    0.46
    ospitals
    0.45
     चिकित्सा
    0.43
    पयोग
    0.43
    pele
    0.43
    嚀
    0.43
    eredith
    0.42
     தொழ
    0.42
    POSITIVE LOGITS
     another
    0.54
     Another
    0.50
    另一个
    0.50
     transacción
    0.45
     announcement
    0.44
     expressed
    0.42
     一个
    0.42
     ANOTHER
    0.42
     Announcement
    0.42
     আনুষ্ঠানিকভাবে
    0.42
    Activations Density 0.000%

    No Known Activations