© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98961
    Prev
    Next
    INDEX
    Explanations

    cruise ship names and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ked
    -0.78
     planters
    -0.77
     partito
    -0.77
    levan
    -0.75
    mandatory
    -0.74
    ྟ
    -0.73
    ਢ
    -0.71
    utete
    -0.70
    OEM
    -0.70
    kko
    -0.70
    POSITIVE LOGITS
     cruise
    1.17
     cru
    0.97
     cruises
    0.96
    Cru
    0.85
     Cru
    0.81
     Viv
    0.79
     Viva
    0.75
     Запад
    0.74
     MSC
    0.74
    ینی
    0.72
    Activations Density 0.010%

    No Known Activations