© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 9683
    Prev
    Next
    INDEX
    Explanations

    . , *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÉS
    0.95
    
    0.94
    <unused569>
    0.93
     Sánchez
    0.85
    
    0.84
    <unused678>
    0.83
     Bradbury
    0.82
     масштаб
    0.81
     cendré
    0.80
    
    0.79
    POSITIVE LOGITS
      
    1.20
     ,
    1.19
     मैने
    1.06
     नही
    0.97
     ايضا
    0.95
     उन्ह
    0.93
     लोगो
    0.93
       
    0.90
    ,(
    0.89
     কারন
    0.88
    Activations Density 0.235%

    No Known Activations