© 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. 256229
    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
    ноп
    0.50
     오늘도
    0.48
    ảm
    0.47
    рят
    0.46
    ură
    0.45
     samedi
    0.45
    暠
    0.44
    ար
    0.44
    плей
    0.43
    آن
    0.43
    POSITIVE LOGITS
     Magnesium
    0.46
     Manganese
    0.45
    মাতে
    0.43
     Cypress
    0.42
     Metric
    0.42
     Generation
    0.41
     requisito
    0.41
     diment
    0.39
    藕
    0.39
     Dmit
    0.39
    Activations Density 0.001%

    No Known Activations