© 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. 249349
    Prev
    Next
    INDEX
    Explanations

    financial savings and patents

    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
    南極
    0.51
    н
    0.49
    matplotlib
    0.49
    蔣
    0.48
    lockSeconds
    0.48
    াহিয়া
    0.47
    獵
    0.46
    Entonces
    0.46
     പിറ
    0.46
    ्ट
    0.46
    POSITIVE LOGITS
    تی
    0.47
     Territory
    0.46
    ми
    0.45
    साठी
    0.43
    /
    0.42
    <0x0D>
    0.42
     وتح
    0.42
     Superior
    0.42
     Worldwide
    0.42
    ستانی
    0.42
    Activations Density 0.000%

    No Known Activations