© 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. 310
    Prev
    Next
    INDEX
    Explanations

    listing options

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    งาน
    1.71
    т
    1.56
    د
    1.54
     również
    1.48
    д
    1.45
    ۔
    1.30
    ivist
    1.29
    ara
    1.27
    एल
    1.27
    り
    1.27
    POSITIVE LOGITS
     whatnot
    1.75
     equivalently
    1.50
     вовсе
    1.30
     procé
    1.21
    не
    1.17
     biasa
    1.16
    l
    1.15
    acles
    1.14
     montaña
    1.13
     혹은
    1.12
    Activations Density 0.467%

    No Known Activations