© 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. 40-GEMMASCOPE-2-RES-262K
    7. 21522
    Prev
    Next
    INDEX
    Explanations

    motorcycle

    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_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
     диф
    0.42
    휋
    0.42
     car
    0.40
    司机
    0.38
     strained
    0.38
     genealogical
    0.38
    ‒
    0.38
    carpet
    0.37
    汽車
    0.37
    =[]
    0.37
    POSITIVE LOGITS
     motorcycle
    2.34
     Motorcycle
    2.19
     motorcycles
    2.06
     motorcycl
    1.95
     motorbike
    1.94
     मोटरसाइकिल
    1.94
     Motorcycles
    1.91
    🏍
    1.88
     bike
    1.86
     बाइक
    1.83
    Activations Density 0.015%

    No Known Activations