© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13141
    Prev
    Next
    INDEX
    Explanations

    slave owner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    $(
    1.74
    落在
    1.68
    Cao
    1.66
    entries
    1.64
    geometric
    1.60
    णिमा
    1.59
    ressant
    1.54
    র্গের
    1.54
    ROR
    1.54
    declare
    1.52
    POSITIVE LOGITS
     モ
    1.75
     入れ
    1.75
     proced
    1.73
     リ
    1.71
     intermission
    1.69
     サー
    1.66
     ピ
    1.64
     случилось
    1.64
     パ
    1.62
     toBe
    1.60
    Activations Density 0.120%

    No Known Activations