© 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. 259007
    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
    (':
    0.52
    LuaPush
    0.50
    {
    0.49
    물
    0.49
    裙
    0.49
    SetParameter
    0.49
    {}'.
    0.48
    +{
    0.47
    ('+
    0.47
    និង
    0.47
    POSITIVE LOGITS
     Digital
    0.48
     Tick
    0.48
     Mania
    0.47
     digital
    0.47
     Qual
    0.46
     Pran
    0.46
     passing
    0.46
     Mane
    0.45
     Tic
    0.45
     Artisan
    0.44
    Activations Density 0.000%

    No Known Activations