© 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-65K
    7. 2301
    Prev
    Next
    INDEX
    Explanations

    Day 1:

    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_65k_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
    p
    1.31
    پن
    1.25
     ਲੈ
    1.24
    ｐ
    1.22
     p
    1.18
     gegenüber
    1.17
    creep
    1.16
    로
    1.16
     ਕਰ
    1.16
    err
    1.15
    POSITIVE LOGITS
     composición
    1.61
     doanh
    1.55
     compon
    1.54
     Tatra
    1.48
     agglomer
    1.47
    Laravel
    1.47
    Redis
    1.47
     gian
    1.46
     Maltese
    1.46
    bitat
    1.45
    Activations Density 0.000%

    No Known Activations