© 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. 3244
    Prev
    Next
    INDEX
    Explanations

    differential treatment or favoritism

    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
     సం
    -0.86
     honnête
    -0.85
     membrana
    -0.84
    AYSIA
    -0.82
    lagem
    -0.82
     Caracter
    -0.81
     ترکیب
    -0.81
     ܐ
    -0.81
     minOccurs
    -0.81
    ListNode
    -0.80
    POSITIVE LOGITS
     preferential
    2.70
     differential
    2.19
     treatment
    2.09
     unequal
    2.05
     favor
    1.95
     favou
    1.93
     favored
    1.90
    fav
    1.89
     different
    1.80
     Fav
    1.80
    Activations Density 0.037%

    No Known Activations