© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2739
    Prev
    Next
    INDEX
    Explanations

    comparing features in tables

    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
    ouvoir
    0.44
    िनय
    0.43
    первых
    0.41
    oforte
    0.41
    ים
    0.40
    用の
    0.40
    füh
    0.39
    ¬
    0.39
    →</
    0.38
    ’:
    0.38
    POSITIVE LOGITS
     Feature
    0.57
                  
    0.55
                 
    0.54
     Features
    0.54
                     
    0.52
     특징
    0.50
     Characteristics
    0.49
    Features
    0.49
     FEATURE
    0.49
                           
    0.49
    Activations Density 0.010%

    No Known Activations