© 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. 260876
    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
    ال
    0.58
    ج
    0.56
     av
    0.55
     a
    0.54
     İl
    0.53
     With
    0.53
     Eman
    0.52
     Some
    0.51
     Trying
    0.51
     целью
    0.50
    POSITIVE LOGITS
     affairs
    0.77
     sprawy
    0.71
     matters
    0.68
     asunto
    0.66
    g
    0.64
    ার
    0.63
     asuntos
    0.63
     matter
    0.63
    u
    0.62
     AFFAIRS
    0.61
    Activations Density 0.072%

    No Known Activations