© 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. 1589
    Prev
    Next
    INDEX
    Explanations

    slightly modifying descriptions

    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
    밍
    1.98
    وك
    1.79
    εδ
    1.72
     nimet
    1.72
     kost
    1.69
    맴
    1.68
     zlo
    1.67
     ياس
    1.61
    θεση
    1.60
    چنین
    1.60
    POSITIVE LOGITS
     Florent
    2.39
     Angelina
    2.23
     Rustic
    2.16
    MongoClient
    2.11
    📐
    2.03
    Henry
    1.99
     adventurer
    1.98
    authentic
    1.98
     Eliza
    1.97
    Rustic
    1.96
    Activations Density 0.538%

    No Known Activations