© 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. 454
    Prev
    Next
    INDEX
    Explanations

    punctuation and quotes

    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
     不是
    1.79
     啊
    1.70
     你
    1.65
     不能
    1.64
     也
    1.61
     就是
    1.61
     哦
    1.61
     因此
    1.57
     把
    1.56
     套
    1.55
    POSITIVE LOGITS
    dengan
    1.37
    tidak
    1.30
    dalam
    1.30
     लगाएंगे
    1.29
    হইতে
    1.29
    टेगरी
    1.29
    Selain
    1.28
    ग्वि
    1.26
    तोंडा
    1.26
    पहरण
    1.24
    Activations Density 0.101%

    No Known Activations