© 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. 145389
    Prev
    Next
    INDEX
    Explanations

    way you speak

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

    supply, investment, connections

    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
    シリーズ
    0.49
    HomeController
    0.47
    ைகளுக்கு
    0.46
     Carousel
    0.45
     ڈپ
    0.45
    Не
    0.45
    Одно
    0.44
    猫
    0.43
    Ồ
    0.43
    Ж
    0.43
    POSITIVE LOGITS
    l
    0.54
    extend
    0.52
     busque
    0.51
     einem
    0.50
    b
    0.49
    k
    0.48
     vean
    0.46
     repas
    0.46
    mäss
    0.46
     rek
    0.46
    Activations Density 0.000%

    No Known Activations