© 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. 22-GEMMASCOPE-RES-131K
    7. 34588
    Prev
    Next
    INDEX
    Explanations

    difference calculation

    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
    dotti
    -0.88
    kově
    -0.84
    lecteur
    -0.83
    zden
    -0.79
    ječ
    -0.79
    irsten
    -0.77
     adolescentes
    -0.76
    ੂੰ
    -0.75
     povez
    -0.74
    cmake
    -0.73
    POSITIVE LOGITS
     difference
    1.68
    difference
    1.37
     transition
    1.26
     intervening
    1.26
     differences
    1.20
    Difference
    1.17
     Difference
    1.11
     change
    1.08
     разница
    1.04
    transition
    1.01
    Activations Density 0.086%

    No Known Activations