© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 39808
    Prev
    Next
    INDEX
    Explanations

    advanced computing capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    汚れ
    0.55
     decoration
    0.51
     textile
    0.49
     femininity
    0.47
     extravaganza
    0.47
     diminution
    0.47
     reduction
    0.46
    🥰
    0.46
     भक्ति
    0.46
     pyaar
    0.46
    POSITIVE LOGITS
     Investigators
    0.50
     investigators
    0.47
     desenvolved
    0.47
     potencialmente
    0.46
     Scientist
    0.46
     funcionários
    0.46
     pilotos
    0.46
     utilisateurs
    0.46
     Veterinary
    0.46
     Computational
    0.45
    Activations Density 0.022%

    No Known Activations