© 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. 1819
    Prev
    Next
    INDEX
    Explanations

    least privilege access

    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
    nya
    0.88
     slings
    0.83
    ক্ষণে
    0.79
    re
    0.76
    説明
    0.72
    まだ
    0.71
    俺
    0.71
     Siamese
    0.69
     monstros
    0.67
     kleiner
    0.67
    POSITIVE LOGITS
     kaliteli
    1.35
     读取
    1.26
    ော
    1.26
    ᴡ
    1.25
     tốc
    1.23
     גבוה
    1.22
     marginRight
    1.22
    βα
    1.22
     cấp
    1.22
    
    1.22
    Activations Density 0.535%

    No Known Activations