© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93601
    Prev
    Next
    INDEX
    Explanations

    variable comparison and logical 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
     is
    -1.48
     was
    -1.26
    ,
    -1.15
    =
    -1.08
     =
    -0.93
     completa
    -0.92
     Ried
    -0.85
    与
    -0.81
     насос
    -0.81
     into
    -0.81
    POSITIVE LOGITS
     then
    1.92
     &&
    1.59
     or
    1.42
     entonces
    1.41
     THEN
    1.35
     então
    1.34
     ||
    1.34
     ||
    1.32
    Тогда
    1.29
     &&
    1.27
    Activations Density 0.018%

    No Known Activations