© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35857
    Prev
    Next
    INDEX
    Explanations

    unsigned integer types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ویژگی
    -1.59
     parfü
    -1.57
     nadru
    -1.52
     telefonu
    -1.52
     salonu
    -1.52
    を注文
    -1.50
     biela
    -1.49
    موس
    -1.49
    مقدمه
    -1.49
     排骨
    -1.48
    POSITIVE LOGITS
    u
    1.66
    f
    1.59
    ta
    1.53
    k
    1.51
    en
    1.48
     J
    1.48
     P
    1.45
    y
    1.42
    m
    1.42
     --
    1.42
    Activations Density 0.005%

    No Known Activations