© 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. 10-GEMMASCOPE-RES-131K
    7. 57505
    Prev
    Next
    INDEX
    Explanations

    random number generation

    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_10/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
    J
    -1.54
     nulla
    -1.37
     trésor
    -1.33
    襯
    -1.32
     иной
    -1.32
    』『
    -1.32
    U
    -1.31
    냑
    -1.28
    of
    -1.27
    élève
    -1.26
    POSITIVE LOGITS
     by
    1.68
     from
    1.60
    닮
    1.55
    屉
    1.48
    ЕРИ
    1.41
     signifikan
    1.41
     vooral
    1.38
     milyen
    1.38
     zelfs
    1.37
    šča
    1.37
    Activations Density 0.018%

    No Known Activations