© 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. 57162
    Prev
    Next
    INDEX
    Explanations

    verb + common followed word

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

    fix issues when merged

    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
    ب
    0.47
    สมาชิก
    0.45
     Orrell
    0.44
    من
    0.44
    ซึ่ง
    0.43
    برا
    0.43
     elapse
    0.43
    الس
    0.43
     aggreg
    0.42
     IPCC
    0.42
    POSITIVE LOGITS
    ៌
    0.55
    itario
    0.51
     நடித்து
    0.49
     casualties
    0.49
    whale
    0.49
     ตาย
    0.49
     vengeance
    0.48
     quảng
    0.48
    gameOver
    0.48
     retaliation
    0.47
    Activations Density 0.000%

    No Known Activations