© 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. 64612
    Prev
    Next
    INDEX
    Explanations

    entrepreneurs, camp, Isaiah, links, tools, ', first, ., is, World

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

    personal costs and regulations

    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
    这一
    0.49
     accidentally
    0.48
     coldly
    0.46
     overhe
    0.46
    她们
    0.45
    網
    0.44
    委托
    0.44
     destitute
    0.43
    ئات
    0.43
     involuntarily
    0.43
    POSITIVE LOGITS
     ৬০
    0.55
     হের
    0.55
    cumsum
    0.55
     맛있
    0.54
     ব্রাজ
    0.50
     Пів
    0.50
     forearm
    0.50
     通販
    0.50
    _{+}-
    0.50
     크게
    0.49
    Activations Density 0.000%

    No Known Activations