© 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. 7230
    Prev
    Next
    INDEX
    Explanations

    ships, fleets, and manufacturing

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

    building and deploying technology

    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
     hastalık
    0.55
    坫
    0.55
    肤
    0.54
     मूत्र
    0.54
    情节
    0.54
    RatingDiff
    0.54
    肌肤
    0.53
     Dạ
    0.53
    ámicas
    0.53
    韫
    0.53
    POSITIVE LOGITS
     tonnage
    0.86
     fleet
    0.85
     shipyard
    0.84
     shipbuilding
    0.83
     modular
    0.82
     fleets
    0.81
    建造
    0.81
     deliveries
    0.80
     turnkey
    0.80
     ships
    0.77
    Activations Density 0.261%

    No Known Activations