© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13958
    Prev
    Next
    INDEX
    Explanations

    death

    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_7_width_16k_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
    楯
    2.28
    鹉
    2.27
    蛳
    2.26
    절
    2.26
    ㄠ
    2.25
    ki
    2.23
    saan
    2.22
    蜓
    2.20
     fēng
    2.18
    ılabilir
    2.17
    POSITIVE LOGITS
    центри
    3.06
    
    2.74
    Қ
    2.64
    йн
    2.61
    🧍
    2.58
    ي
    2.45
     विशेषताएं
    2.45
    FromNib
    2.44
     Biro
    2.42
     гель
    2.40
    Activations Density 0.007%

    No Known Activations