© 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-65K
    7. 4033
    Prev
    Next
    INDEX
    Explanations

    architecture and construction

    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_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
    mainloop
    0.49
    rownames
    0.46
     trivially
    0.46
     hurtful
    0.46
     nltk
    0.44
    oxidase
    0.43
     poisonous
    0.43
    𝓈
    0.43
    aktionen
    0.43
    experiments
    0.43
    POSITIVE LOGITS
     Revit
    1.46
     BIM
    1.38
     Architectural
    1.30
    施工
    1.24
     LEED
    1.23
     Construction
    1.23
     architectural
    1.18
     geotechnical
    1.13
    建筑
    1.12
     Architects
    1.10
    Activations Density 0.166%

    No Known Activations