© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 749
    Prev
    Next
    INDEX
    Explanations

    questions asking user's state or intent

    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_17_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
     Print
    0.91
     Constructed
    0.78
    Print
    0.78
     c
    0.75
     teen
    0.73
     अनुप
    0.72
    <
    0.70
     Teen
    0.69
     Student
    0.69
    Student
    0.68
    POSITIVE LOGITS
    umbr
    1.06
    IRCONIUM
    1.01
    insurance
    0.97
     Viscount
    0.96
     보험
    0.92
    AppCompatTheme
    0.92
     公司
    0.91
    PHPExcel
    0.91
    认
    0.90
     Gloucestershire
    0.90
    Activations Density 0.044%

    No Known Activations