© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5283
    Prev
    Next
    INDEX
    Explanations

    Russian conjunctions and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    Okay, let's analyze

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_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
     Кстати
    0.39
     Incidentally
    0.38
     übrigens
    0.37
     infine
    0.35
     stil
    0.34
    ..'
    0.34
     again
    0.33
     .*
    0.33
    .).
    0.33
    Incidentally
    0.33
    POSITIVE LOGITS
     例文帳に追加
    0.75
    例文帳に追加
    0.73
    <0xC2>
    0.65
     […]
    0.48
     Whilst
    0.47
         
    0.47
    Whilst
    0.47
       
    0.46
     Букмекерлар
    0.46
      
    0.45
    Activations Density 1.384%

    No Known Activations