© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 165
    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_12_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
    빱
    0.90
    ъем
    0.89
     cultivos
    0.89
     pTM
    0.88
     प्रोवाइड
    0.82
     consecutivos
    0.82
     đỉnh
    0.81
     WUE
    0.80
    перы
    0.80
     ведет
    0.80
    POSITIVE LOGITS
    time
    0.93
    ()=>{
    0.88
    province
    0.88
    energy
    0.87
    type
    0.86
    use
    0.84
    quad
    0.84
    ان
    0.84
    faith
    0.84
     mathrm
    0.83
    Activations Density 0.000%

    No Known Activations