© 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. 12302
    Prev
    Next
    INDEX
    Explanations

    JavaScript DOM manipulation

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

    javascript code manipulation

    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
    毅
    0.54
    বিধি
    0.50
    Creo
    0.49
    INTRODUCTION
    0.48
    MEDICAL
    0.47
    ів
    0.44
    釀
    0.44
    ZE
    0.44
     ಸಂಗೀತ
    0.44
    лад
    0.44
    POSITIVE LOGITS
     setTimeout
    0.46
     localStorage
    0.45
     reunions
    0.45
    innerHeight
    0.44
     clearInterval
    0.44
     tries
    0.42
     parseInt
    0.42
    allenge
    0.41
     $('.
    0.41
     window
    0.41
    Activations Density 0.000%

    No Known Activations