© 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. 91390
    Prev
    Next
    INDEX
    Explanations

    differential correction and positioning

    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
    дыду
    -0.71
    argp
    -0.71
     useful
    -0.71
    iscope
    -0.71
    uego
    -0.71
     unirse
    -0.69
    hör
    -0.69
     storico
    -0.68
    peicher
    -0.67
     Hebrew
    -0.66
    POSITIVE LOGITS
     differential
    1.16
     correctional
    1.10
     Differential
    1.10
     correction
    1.07
     corrections
    1.03
     centimeter
    1.03
     differentially
    1.01
    Differential
    0.97
     diffé
    0.91
    differential
    0.90
    Activations Density 0.016%

    No Known Activations