© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13856
    Prev
    Next
    INDEX
    Explanations

    do you / do they questions

    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_7_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
     نق
    1.63
     rode
    1.52
    عی
    1.49
     احسن
    1.47
     ..
    1.45
    אי
    1.44
     Error
    1.42
    ↵
    1.42
     ERROR
    1.42
     later
    1.41
    POSITIVE LOGITS
    oMatrix
    1.89
     posuere
    1.81
     programación
    1.69
    পাত্র
    1.65
     स्लाइड्स
    1.65
    arello
    1.64
     armazenamento
    1.63
    宽高
    1.62
     sagittis
    1.62
    avu
    1.61
    Activations Density 0.006%

    No Known Activations