© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13778
    Prev
    Next
    INDEX
    Explanations

    illustrative or simplified examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     robuste
    1.57
     röm
    1.47
     demikian
    1.47
     recour
    1.47
     amplio
    1.43
     barbar
    1.43
     inve
    1.43
    </b>
    1.40
     bloque
    1.38
     vielfält
    1.38
    POSITIVE LOGITS
     ดู
    1.79
    <0xF3>
    1.68
     สิ่ง
    1.67
     ЗА
    1.63
     แต่
    1.61
     ตัว
    1.61
     ไม่
    1.60
     อย่าง
    1.58
     За
    1.58
     пра
    1.57
    Activations Density 0.225%

    No Known Activations