© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 5718
    Prev
    Next
    INDEX
    Explanations

    trains and railways

    np_acts-logits-general · gemini-2.5-flash-lite

    trains and railways

    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_53_width_65k_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
     herpes
    0.49
     Herpes
    0.47
    椛
    0.45
    ണേ
    0.42
    苓
    0.40
     healers
    0.40
     Baptism
    0.39
     аллер
    0.38
     rgb
    0.37
     //!
    0.37
    POSITIVE LOGITS
     railway
    3.23
     railroad
    3.14
     rail
    2.97
     railways
    2.97
    Railway
    2.97
     train
    2.95
     Railway
    2.91
     trains
    2.89
     रेलवे
    2.88
    铁路
    2.86
    Activations Density 0.230%

    No Known Activations