© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 252275
    Prev
    Next
    INDEX
    Explanations

    transportation and related activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ig
    0.55
     पाठशाला
    0.51
    даря
    0.51
     получать
    0.50
    лу
    0.49
    u
    0.49
    o
    0.48
     плен
    0.47
    تى
    0.46
    Repeating
    0.46
    POSITIVE LOGITS
     trasport
    0.49
     transportation
    0.49
     trasporto
    0.45
    ხილ
    0.45
     transport
    0.44
     transportasi
    0.44
    უხ
    0.44
    럭
    0.44
     culinary
    0.43
    넉
    0.43
    Activations Density 0.000%

    No Known Activations