© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30825
    Prev
    Next
    INDEX
    Explanations

    German and European nationalities

    np_acts-logits-general · gemini-2.5-flash-lite

    european

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    i
    0.60
    e
    0.54
    b
    0.53
    ej
    0.50
     conson
    0.49
    ek
    0.49
    ean
    0.49
    ין
    0.48
    o
    0.48
     pej
    0.47
    POSITIVE LOGITS
     European
    0.79
     German
    0.75
     Europeans
    0.74
     Germans
    0.73
     европей
    0.73
     immigrated
    0.73
     Germany
    0.73
    Germany
    0.71
     Europese
    0.71
    European
    0.70
    Activations Density 0.348%

    No Known Activations