© 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. 40638
    Prev
    Next
    INDEX
    Explanations

    real economic terms

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

    real return and general intelligence

    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
     美
    0.53
     分
    0.50
     別
    0.49
     インテリア
    0.49
     木製
    0.49
     片
    0.49
     家具
    0.47
     Australien
    0.47
     透明
    0.47
     電
    0.47
    POSITIVE LOGITS
    逻
    0.53
    业务
    0.48
    ressive
    0.47
     रीजनिंग
    0.45
     luật
    0.43
     consegu
    0.42
    Доброго
    0.42
    क्रोश
    0.42
    数十
    0.42
    ными
    0.41
    Activations Density 0.000%

    No Known Activations