© 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. 52570
    Prev
    Next
    INDEX
    Explanations

    saint laurent

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

    describes or defines characteristics

    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
     इज़
    0.49
     keing
    0.49
     Benim
    0.48
     Христо
    0.47
     месе
    0.47
     возникновения
    0.47
    侕
    0.47
    口碑
    0.47
     हळ
    0.47
     Ispol
    0.47
    POSITIVE LOGITS
    ’
    0.49
     commenter
    0.46
     parli
    0.46
    ORT
    0.45
     finalists
    0.45
     bottled
    0.44
     bott
    0.44
     cube
    0.44
     BOUND
    0.43
     SK
    0.42
    Activations Density 0.000%

    No Known Activations