© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1275
    Prev
    Next
    INDEX
    Explanations

    regular expression

    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
    썩
    1.32
     mão
    1.32
    кож
    1.29
    segu
    1.19
     пробу
    1.19
     чтоб
    1.19
     сек
    1.17
    퍽
    1.17
     μας
    1.17
     як
    1.16
    POSITIVE LOGITS
     classifications
    2.14
     dwellings
    2.10
     pharmaceutical
    2.09
     surpluses
    2.08
     compounds
    2.02
     centroids
    2.00
     pharmaceuticals
    2.00
     geospatial
    2.00
     odors
    1.97
     citizenship
    1.96
    Activations Density 0.345%

    No Known Activations