© 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. 36204
    Prev
    Next
    INDEX
    Explanations

    opposite pairs and counterparts

    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
    でない
    -0.86
    chés
    -0.83
     gesche
    -0.80
    Herzliche
    -0.79
    newblock
    -0.79
    Implement
    -0.79
    Environment
    -0.78
    enig
    -0.78
    (>
    -0.78
    }{*}{
    -0.77
    POSITIVE LOGITS
     opposite
    1.25
     reversed
    1.20
     Opposite
    1.06
     reverse
    1.05
    Opposite
    0.94
     flipped
    0.94
     counterpart
    0.93
    flipped
    0.91
     reverses
    0.91
     reversal
    0.91
    Activations Density 0.058%

    No Known Activations