© 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. 181
    Prev
    Next
    INDEX
    Explanations

    code blocks and special characters

    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
    bbR
    1.05
     harnessed
    0.99
    -”
    0.97
     more
    0.96
     mot
    0.88
    pple
    0.88
     concentrated
    0.87
     proportional
    0.86
     obl
    0.86
     co
    0.86
    POSITIVE LOGITS
    ↵
    1.78
     นับ
    1.66
     ricerche
    1.63
    ・・
    1.58
     meninggal
    1.57
     berfungsi
    1.56
     ส่ง
    1.56
     Tidak
    1.56
     زید
    1.55
    MouseClicked
    1.54
    Activations Density 0.004%

    No Known Activations