© 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. 260079
    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
    ه
    0.55
    ور
    0.52
    Sandra
    0.51
    ونا
    0.49
    Patricia
    0.48
    れている
    0.48
    Janet
    0.48
    Джек
    0.47
    Tenemos
    0.47
    盤
    0.47
    POSITIVE LOGITS
     l
    0.62
     Quebec
    0.60
    for
    0.54
     Surgery
    0.54
     XXIII
    0.52
     slučaj
    0.51
    arly
    0.50
     XIX
    0.48
     結婚
    0.48
     colori
    0.48
    Activations Density 0.000%

    No Known Activations