© 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. 9662
    Prev
    Next
    INDEX
    Explanations

    `only` or `from` patterns

    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
    oes
    1.29
    o
    1.28
    and
    1.17
    ive
    1.06
    fm
    1.05
    er
    1.03
    a
    1.03
    uter
    1.00
    never
    1.00
    ft
    0.96
    POSITIVE LOGITS
     非
    1.56
     CHART
    1.54
     初始化
    1.53
     Determining
    1.50
     /(\
    1.47
     कक्क
    1.46
    DLJ
    1.43
     itertools
    1.43
     tqdm
    1.41
     Meteorological
    1.41
    Activations Density 0.003%

    No Known Activations