© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2317
    Prev
    Next
    INDEX
    Explanations

    multi-language identifiers and code segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    ストラップ
    0.73
    자
    0.72
    作者
    0.71
    ússia
    0.71
     Diagnose
    0.71
     trại
    0.70
     масте
    0.69
     understands
    0.68
     plasm
    0.67
    пой
    0.67
    POSITIVE LOGITS
    canon
    0.65
     बुध
    0.62
     ৬৮
    0.62
     cess
    0.60
    beer
    0.56
     امریک
    0.56
     оборудование
    0.56
    般
    0.54
    iesen
    0.54
    cessing
    0.54
    Activations Density 0.130%

    No Known Activations