© 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. 57664
    Prev
    Next
    INDEX
    Explanations

    them self

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

    jpeg artifacts and mental models

    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
    ни
    0.56
    覆
    0.51
    匹配
    0.49
    CUSSION
    0.49
    пи
    0.47
    веден
    0.46
    ارا
    0.46
    霰
    0.45
    幔
    0.43
    পি
    0.42
    POSITIVE LOGITS
     histórico
    0.52
     quinze
    0.50
     twenty
    0.49
    emptyset
    0.48
     realistically
    0.48
     moglie
    0.48
     équipes
    0.47
     estómago
    0.47
    гүнкү
    0.47
     monasteries
    0.47
    Activations Density 0.000%

    No Known Activations