© 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. 386
    Prev
    Next
    INDEX
    Explanations

    words like Walmart, welcome, make, RISC

    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
     för
    0.94
    )](
    0.89
    För
    0.89
    ()<
    0.88
     durchgeführt
    0.88
     için
    0.85
    >());
    0.85
    มี
    0.84
     från
    0.84
    นี้
    0.83
    POSITIVE LOGITS
     D
    1.27
     T
    1.20
     S
    1.13
     helpline
    1.13
     Beatles
    1.09
     tshirt
    1.08
     B
    1.06
    gates
    1.06
     M
    1.05
     U
    1.05
    Activations Density 0.519%

    No Known Activations