© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1955
    Prev
    Next
    INDEX
    Explanations

    lots of images

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    ed
    0.44
            
    0.43
      
    0.43
    ll
    0.43
          
    0.42
    ]
    0.40
     {
    0.40
           
    0.39
       
    0.39
    nd
    0.39
    POSITIVE LOGITS
    عاية
    0.36
     الشه
    0.33
     funkcjon
    0.33
    يو
    0.32
     управления
    0.32
     للم
    0.32
     bekerja
    0.31
     crescita
    0.31
     حياة
    0.31
     politika
    0.31
    Activations Density 0.259%

    No Known Activations