© 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. 31-GEMMASCOPE-2-RES-262K
    7. 259158
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     tumeurs
    0.51
     manzanas
    0.49
    
    0.47
    ドリ
    0.47
     bandas
    0.47
     gouttes
    0.46
     Бан
    0.46
     mundo
    0.45
     nombreuses
    0.45
     enlaces
    0.45
    POSITIVE LOGITS
    负责
    0.46
    죠
    0.44
    owing
    0.43
    함으로써
    0.43
    apolis
    0.42
    ochemical
    0.41
     Moff
    0.41
    負責
    0.41
    信息
    0.40
    重要
    0.40
    Activations Density 0.000%

    No Known Activations