© 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. 260556
    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
    FEL
    0.52
    욌
    0.51
    ții
    0.50
     матри
    0.48
    ৬
    0.47
    SIGNAL
    0.46
    部分は
    0.46
     phận
    0.46
    хо
    0.46
    ги
    0.46
    POSITIVE LOGITS
    ensch
    0.54
    nie
    0.46
    翱
    0.43
     croire
    0.43
    preis
    0.42
     Leuven
    0.42
     getColor
    0.42
     الوا
    0.41
     تعدد
    0.41
     Backward
    0.40
    Activations Density 0.001%

    No Known Activations