© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5674
    Prev
    Next
    INDEX
    Explanations

    QApplication in PyQt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     पादुकोण
    1.55
     ha
    1.54
    ӗ
    1.51
     прис
    1.51
     сло
    1.47
    การ
    1.44
    琶
    1.42
    чь
    1.40
    를
    1.39
    ية
    1.37
    POSITIVE LOGITS
    বৃত্তি
    1.88
     nond
    1.82
    ាញ់
    1.81
    ধার
    1.81
    琲
    1.77
     亻
    1.77
    ジュアル
    1.77
    帳
    1.76
    hmm
    1.74
    sync
    1.74
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.