© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8638
    Prev
    Next
    INDEX
    Explanations

    building systems installation and services

    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_40_width_16k_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
     sprawl
    0.52
     hilly
    0.48
     공간
    0.46
     простран
    0.45
     space
    0.44
     prostor
    0.44
    Ꭽ
    0.43
     highway
    0.41
     embankment
    0.41
     맨
    0.41
    POSITIVE LOGITS
     installed
    0.79
     install
    0.73
     Installed
    0.72
     instalado
    0.71
     systems
    0.71
     plumbing
    0.71
    系统的
    0.69
    installed
    0.68
     वायरिंग
    0.68
     Systems
    0.67
    Activations Density 0.112%

    No Known Activations