© 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. 54150
    Prev
    Next
    INDEX
    Explanations

    negative numbers and arithmetic

    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
    дава
    -1.05
     tragé
    -1.01
    ingeki
    -0.90
    艶
    -0.88
    нял
    -0.88
     vál
    -0.88
     mostaza
    -0.87
    ))^
    -0.87
    inspace
    -0.87
    quête
    -0.87
    POSITIVE LOGITS
    even
    1.20
     any
    1.08
     many
    0.98
     even
    0.97
    甚至
    0.95
    tiness
    0.93
     (-)
    0.90
    prender
    0.90
     любом
    0.89
    ticism
    0.89
    Activations Density 0.049%

    No Known Activations