© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11310
    Prev
    Next
    INDEX
    Explanations

    product and sum notation

    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_31_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
    empio
    0.65
     yada
    0.63
    rawValue
    0.59
     ಆನಿ
    0.59
     آیت
    0.58
    ༣
    0.58
    тони
    0.57
    ienda
    0.57
     مقدار
    0.57
    oer
    0.57
    POSITIVE LOGITS
     носи
    0.59
     Revis
    0.55
     brilliant
    0.54
     consultants
    0.52
     Inventors
    0.52
    文
    0.52
     carrying
    0.51
     revisar
    0.50
     विभागा
    0.50
     evit
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.