© 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. 62844
    Prev
    Next
    INDEX
    Explanations

    subtract, subtraction, or related operations

    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
    lceil
    -0.74
     +
    -0.73
    CheckedChanged
    -0.73
    Ricky
    -0.72
     pup
    -0.69
    겔
    -0.68
    hammad
    -0.68
     Ata
    -0.67
    Pamela
    -0.67
     duplicate
    -0.67
    POSITIVE LOGITS
     subtract
    4.53
     subtraction
    4.53
     subtracting
    4.47
     subtracted
    4.44
     subtra
    4.31
    subtract
    4.03
     Subtract
    3.86
    Subtract
    3.78
     Subtraction
    3.47
     deduct
    3.02
    Activations Density 0.073%

    No Known Activations