© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14790
    Prev
    Next
    INDEX
    Explanations

    add milk

    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_13_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
     Yamada
    1.39
    ①
    1.36
     superconducting
    1.29
     Kondo
    1.26
     Sutter
    1.26
     Miyazaki
    1.25
     Ulm
    1.23
     Augsburg
    1.22
    熊本
    1.21
    沢
    1.21
    POSITIVE LOGITS
     Guyana
    1.73
    Jamaica
    1.61
     disposición
    1.60
     constitución
    1.58
    Caribbean
    1.55
     desirous
    1.54
     אשר
    1.51
     soggetto
    1.50
     Tobago
    1.47
     Barbados
    1.44
    Activations Density 0.425%

    No Known Activations