© 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. 74012
    Prev
    Next
    INDEX
    Explanations

    cruise ships, boats, docking

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

    watercraft and associated 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
     టీ
    0.45
     hysteria
    0.45
     murid
    0.45
     गाड़ी
    0.43
     gruesome
    0.43
    꼰
    0.43
     meisjes
    0.42
    Consentiti
    0.42
     candidature
    0.42
     vliegtuig
    0.41
    POSITIVE LOGITS
     sailboats
    0.65
    🚤
    0.63
     boats
    0.62
    🛥
    0.61
    航
    0.60
     docked
    0.59
    Boat
    0.58
    浮か
    0.57
     docking
    0.57
     marinas
    0.57
    Activations Density 0.162%

    No Known Activations