© 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. 257752
    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
     troch
    0.44
    ەش
    0.43
     세
    0.43
    рем
    0.43
    ირი
    0.43
    덫
    0.43
    ౪
    0.42
     contextos
    0.41
    glieder
    0.41
    
    0.40
    POSITIVE LOGITS
     Championships
    0.54
    ;
    0.49
     Championship
    0.48
     ettiği
    0.47
    ;",
    0.46
    ;"
    0.45
     bậc
    0.45
    ที่เป็น
    0.44
     मर
    0.44
     कीजिएगा
    0.44
    Activations Density 0.001%

    No Known Activations