© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11417
    Prev
    Next
    INDEX
    Explanations

    neural intuition and models

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

    conceptual understanding, intuition, common sense

    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_40_width_16k_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
    rma
    0.48
    menu
    0.47
     menu
    0.47
     .........
    0.46
     menus
    0.45
    笫
    0.45
     élabor
    0.44
     ..........
    0.43
    
    0.43
     somente
    0.42
    POSITIVE LOGITS
     discretized
    0.91
     epsilon
    0.90
     countably
    0.86
     MNIST
    0.84
     intuition
    0.83
     ReLU
    0.81
     Lebesgue
    0.79
     Cauchy
    0.79
     asymptotically
    0.79
     wavefunction
    0.78
    Activations Density 0.103%

    No Known Activations