© 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
    2. Gemma-3-12B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 768
    Prev
    Next
    INDEX
    Explanations

    wx, Medicare, reforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    어요
    0.64
    Código
    0.60
     meinen
    0.56
     ይሆ
    0.56
    −</
    0.55
    ⮚
    0.55
     systému
    0.55
    aginaw
    0.54
    Aku
    0.54
     kodu
    0.54
    POSITIVE LOGITS
    		
    0.59
     اد
    0.57
     さらに
    0.56
     类型
    0.55
    ////////////
    0.54
     reforms
    0.54
     Medicare
    0.54
     Reforms
    0.52
    ////////////////
    0.52
    ၻ
    0.52
    Activations Density 0.152%

    No Known Activations