© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 1846
    Prev
    Next
    INDEX
    Explanations

    effort but worth it

    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
     ’
    1.50
     shed
    1.48
     ,
    1.37
     legitimately
    1.35
     谢
    1.35
     stamp
    1.34
     .
    1.32
     就是
    1.30
    ,
    1.29
     的
    1.28
    POSITIVE LOGITS
    Tidak
    1.99
    Não
    1.88
     nincs
    1.87
    しかし
    1.82
     quantità
    1.78
     sebagainya
    1.78
    Jika
    1.76
    tidak
    1.73
    Selain
    1.73
    Untuk
    1.71
    Activations Density 0.678%

    No Known Activations