© 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. 428
    Prev
    Next
    INDEX
    Explanations

    creative and aesthetic descriptions

    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
    
    2.09
     지난해
    1.68
    跚
    1.63
    职工
    1.63
    츨
    1.61
     것으로
    1.60
     گیرد
    1.59
    anediyl
    1.58
    牞
    1.55
    elementReference
    1.55
    POSITIVE LOGITS
     shitty
    3.19
     fucking
    2.99
     lmao
    2.74
     fucked
    2.64
     fuck
    2.64
    めっちゃ
    2.63
     xD
    2.61
     idk
    2.61
     haha
    2.54
     crappy
    2.46
    Activations Density 2.031%

    No Known Activations