© 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. 49233
    Prev
    Next
    INDEX
    Explanations

    present disclosure invention

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

    learning long sequences

    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
     ہے۔
    0.57
    汋
    0.55
     проекта
    0.52
     گی۔
    0.48
     цієї
    0.47
     продукта
    0.46
    毂
    0.46
     процесса
    0.46
     дальней
    0.45
     осталось
    0.44
    POSITIVE LOGITS
    0.47
     mor
    0.46
    kod
    0.45
     I
    0.44
     traf
    0.44
    atoi
    0.44
     var
    0.44
     illeg
    0.43
     zeit
    0.43
     Lim
    0.42
    Activations Density 0.000%

    No Known Activations