© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4662
    Prev
    Next
    INDEX
    Explanations

    Combine or represent based on context

    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_24_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
     valamint
    0.75
     nonché
    0.74
     sowie
    0.73
     daarmee
    0.71
    ١
    0.71
     werd
    0.70
     gleich
    0.69
     solamente
    0.69
     beserta
    0.69
     serta
    0.68
    POSITIVE LOGITS
    不同的
    0.87
    有
    0.73
    人的
    0.72
    具体的
    0.71
    临
    0.71
    欧美
    0.71
     不同
    0.70
    不同
    0.69
    一些
    0.69
     服
    0.69
    Activations Density 0.029%

    No Known Activations