© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77427
    Prev
    Next
    INDEX
    Explanations

    variables followed by comparison operators

    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_34/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
     equal
    -1.99
     equals
    -1.60
     Equal
    -1.56
    equal
    -1.55
    Equal
    -1.55
    等于
    -1.40
     рав
    -1.39
    equals
    -1.37
    EQUAL
    -1.20
     equality
    -1.20
    POSITIVE LOGITS
     <=
    1.37
     <
    1.33
     >=
    1.21
     >
    1.16
     
    0.95
      
    0.92
     '_'
    0.90
     plau
    0.87
    LEON
    0.87
     '/')
    0.86
    Activations Density 0.012%

    No Known Activations