© 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. 64292
    Prev
    Next
    INDEX
    Explanations

    earth and its contexts

    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
     statewide
    -0.79
     menú
    -0.78
    เจ้า
    -0.78
     zahrani
    -0.76
    海外
    -0.76
     foreigners
    -0.75
    妖怪
    -0.74
    getMinutes
    -0.72
     nghị
    -0.72
     foreign
    -0.71
    POSITIVE LOGITS
     Earth
    4.69
    Earth
    3.92
     earth
    3.86
     EARTH
    3.14
    earth
    3.09
     earthly
    3.02
    地球
    2.95
    EARTH
    2.88
     Зем
    2.81
     terrestrial
    2.66
    Activations Density 0.044%

    No Known Activations