© 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. 200607
    Prev
    Next
    INDEX
    Explanations

    Dropout, momentum, pooling, attenuator

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

    dropout layer application

    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
    Closing
    0.47
    BANNER
    0.46
    ג
    0.46
     transact
    0.46
    ByCategory
    0.45
    ժ
    0.43
    γγρα
    0.43
     tonnage
    0.43
    ל
    0.42
     converge
    0.42
    POSITIVE LOGITS
     aplicado
    0.48
     selepas
    0.44
     شدید
    0.43
     Aids
    0.43
     نواز
    0.42
     Percentage
    0.41
     dampers
    0.41
     Syndrome
    0.41
    Dropout
    0.41
     جلوگیری
    0.41
    Activations Density 0.000%

    No Known Activations