© 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. 25064
    Prev
    Next
    INDEX
    Explanations

    colonial trade and taxation

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

    resistance and taxes

    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
     initializer
    0.48
     সিভি
    0.44
    initializer
    0.43
    অপহরণ
    0.43
     സമൂഹ
    0.43
    掬
    0.41
     समाजा
    0.41
    ಜ್ಜ
    0.41
     ヘッド
    0.40
     initialization
    0.40
    POSITIVE LOGITS
     taxed
    0.50
     tax
    0.47
     British
    0.46
     London
    0.46
     Colonial
    0.44
     Tax
    0.43
    吏
    0.42
     thuế
    0.42
    cks
    0.41
     Britons
    0.41
    Activations Density 0.014%

    No Known Activations