© 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. 53-GEMMASCOPE-2-RES-65K
    7. 5194
    Prev
    Next
    INDEX
    Explanations

    mathematical algorithms and structures

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

    sparse combinatorial problems

    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_53_width_65k_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
     heartache
    0.50
     técnicas
    0.50
     técnica
    0.49
    现代化
    0.49
    💃
    0.49
    PlayerDataCache
    0.48
     daging
    0.48
    🌹
    0.48
     अत्याधुनिक
    0.48
     तरीका
    0.48
    POSITIVE LOGITS
     convex
    0.91
     symmetric
    0.90
     sparse
    0.86
     stochastic
    0.86
     Symmetric
    0.85
     Discrete
    0.83
     matroid
    0.83
    sparse
    0.82
     Markov
    0.82
     lattices
    0.82
    Activations Density 0.063%

    No Known Activations