© 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. 249166
    Prev
    Next
    INDEX
    Explanations

    trading activities

    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
    照片
    0.49
     initially
    0.46
    那个
    0.46
     Initially
    0.45
    自我
    0.45
    ünün
    0.45
    াজন
    0.45
    在
    0.45
     strane
    0.43
     noticeably
    0.43
    POSITIVE LOGITS
     permettant
    0.48
     фут
    0.48
     permettra
    0.47
     doit
    0.47
     segit
    0.47
     tenemos
    0.47
    買う
    0.46
    ॉफ्ट
    0.45
     republic
    0.45
     fuse
    0.45
    Activations Density 0.001%

    No Known Activations