© 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. 31-GEMMASCOPE-2-RES-262K
    7. 37918
    Prev
    Next
    INDEX
    Explanations

    why followed by clause

    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_262k_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
     Text
    0.50
     Publishing
    0.49
     Architektur
    0.49
     Writing
    0.49
     Entwicklung
    0.49
     History
    0.48
    ęb
    0.48
    𝐚
    0.48
    ഒരു
    0.48
     Details
    0.48
    POSITIVE LOGITS
     intox
    0.54
     stimulants
    0.54
     satiety
    0.54
     detoxification
    0.50
     profitability
    0.49
     haircuts
    0.49
     globules
    0.48
     consumables
    0.47
     glycolysis
    0.47
     aerobic
    0.46
    Activations Density 0.002%

    No Known Activations