© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2797
    Prev
    Next
    INDEX
    Explanations

    spark, pump, smaug, atp, bloom, flush

    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_65k_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
    ding
    1.83
    𝘵
    1.79
    ds
    1.63
    ls
    1.61
    lt
    1.56
    ther
    1.52
    nya
    1.52
    dua
    1.50
    ti
    1.49
    𝘳
    1.48
    POSITIVE LOGITS
    ی
    2.10
    м
    2.09
    ০
    1.90
    า
    1.77
    й
    1.73
    ం
    1.71
     totalPrice
    1.68
    ン
    1.66
    quela
    1.64
    ुभ
    1.57
    Activations Density 0.141%

    No Known Activations