© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8782
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     रिटायर
    0.58
    砍
    0.56
    flowLayoutPanel
    0.55
    corto
    0.54
    たた
    0.53
    測試
    0.53
    人事
    0.53
    पिंग
    0.52
     पान
    0.51
    说明
    0.51
    POSITIVE LOGITS
    র্জ
    0.57
     έν
    0.57
    ellini
    0.52
    蓋
    0.52
     zapewn
    0.52
    ahrenheit
    0.51
    achs
    0.51
     элементы
    0.51
    akel
    0.51
    omba
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.