© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3786
    Prev
    Next
    INDEX
    Explanations

    severe penalties or consequences

    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
    forRoot
    2.87
    qu
    2.82
    랐
    2.65
    effort
    2.63
    setView
    2.58
    
    2.54
    ائق
    2.47
    room
    2.39
     MyHomePage
    2.37
    ForResult
    2.37
    POSITIVE LOGITS
    ી
    3.45
    ার্জ
    3.28
    ક્ટ
    2.96
    ያንዳንዱ
    2.86
    仴
    2.86
    বারেই
    2.78
     preimage
    2.75
    eep
    2.74
    گزاری
    2.74
    ر
    2.73
    Activations Density 0.033%

    No Known Activations