© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39526
    Prev
    Next
    INDEX
    Explanations

    ethnic groups and nationalities

    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_10/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
     the
    -1.50
     their
    -1.38
     its
    -1.29
    支払
    -1.20
     transmisión
    -1.19
     another
    -1.16
    ஂ
    -1.16
     this
    -1.16
     امريكا
    -1.16
    ropy
    -1.15
    POSITIVE LOGITS
     are
    1.82
     bahkan
    1.48
     даже
    1.34
     keď
    1.33
     sogar
    1.27
     حتی
    1.27
     peo
    1.25
     hvid
    1.24
     особенно
    1.23
     illustrationer
    1.23
    Activations Density 0.200%

    No Known Activations