© 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. 192126
    Prev
    Next
    INDEX
    Explanations

    he had

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

    you focus on assumptions

    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
     позволяет
    0.52
     permits
    0.48
     です
    0.47
     pozwala
    0.46
     （
    0.46
     sağlar
    0.45
     обеспечивает
    0.45
     લ
    0.45
    应用程序
    0.45
     环境
    0.43
    POSITIVE LOGITS
     overrated
    0.58
     defam
    0.50
     hated
    0.49
     insulted
    0.47
     tendances
    0.47
     ebben
    0.47
     disgr
    0.46
     domine
    0.44
    嫉
    0.44
     emberek
    0.44
    Activations Density 0.001%

    No Known Activations