© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10726
    Prev
    Next
    INDEX
    Explanations

    list items or questions

    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_7_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
    न्ड
    2.77
    श्किल
    2.70
    TableHeader
    2.61
    footed
    2.58
     $(`.
    2.54
     médioc
    2.52
     бассей
    2.51
    
    2.49
    ুপ্ত
    2.45
    🄴
    2.39
    POSITIVE LOGITS
     chóng
    2.00
     mcm
    1.93
    ork
    1.92
     таки
    1.87
     res
    1.87
    šnje
    1.85
    szak
    1.83
    Tags
    1.79
     inclusions
    1.78
    واز
    1.76
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.