© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10691
    Prev
    Next
    INDEX
    Explanations

    infrastructure components 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
    經濟
    0.48
     अवि
    0.48
     economica
    0.46
    conom
    0.46
    财产
    0.46
    啬
    0.45
     workman
    0.44
     énorm
    0.44
     herk
    0.44
    蚁
    0.44
    POSITIVE LOGITS
     transmission
    0.52
     microwave
    0.52
     radial
    0.51
     LNG
    0.51
     fiber
    0.50
     fibre
    0.49
     mini
    0.49
     terminal
    0.48
     submarine
    0.48
     solar
    0.48
    Activations Density 0.093%

    No Known Activations