© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5183
    Prev
    Next
    INDEX
    Explanations

    printable educational worksheets

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

    generating drafts or options

    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_53_width_65k_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
    }^{[
    0.50
    idered
    0.46
    ServletException
    0.40
     decisively
    0.39
    [,
    0.39
     سما
    0.38
     بج
    0.38
    ceased
    0.38
    (',');
    0.37
     intelligents
    0.37
    POSITIVE LOGITS
     printable
    1.33
     worksheets
    1.24
     Printable
    1.21
     worksheet
    1.20
     Editable
    1.09
     editable
    1.07
     Worksheet
    1.05
     lesson
    0.98
    printable
    0.97
    Lesson
    0.91
    Activations Density 0.116%

    No Known Activations