© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 32323
    Prev
    Next
    INDEX
    Explanations

    code/technical text

    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_40_width_262k_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
     behind
    0.63
     detrás
    0.62
     derrière
    0.61
    Behind
    0.61
    behind
    0.55
     dietro
    0.52
     Behind
    0.49
     뒤
    0.43
     atrás
    0.43
     sientes
    0.41
    POSITIVE LOGITS
          
    0.46
         
    0.46
       
    0.42
     আবদুল্লাহ
    0.42
    菊
    0.42
    臂
    0.38
     verpflichtet
    0.37
              
    0.36
    凭
    0.36
     Typing
    0.36
    Activations Density 0.004%

    No Known Activations