© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2364
    Prev
    Next
    INDEX
    Explanations

    Texas A&M University

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     Overlay
    0.67
    Graduate
    0.67
     Graduate
    0.66
     Faculty
    0.64
     আশ্বাস
    0.64
    صیلی
    0.63
     Palaiseau
    0.63
     ధ
    0.63
     overlay
    0.63
    ೀನ
    0.63
    POSITIVE LOGITS
     Midwestern
    1.09
     Northern
    1.05
    Northern
    1.01
     Mississippi
    1.01
     Louisiana
    0.98
     Eastern
    0.98
    Eastern
    0.97
     Arkansas
    0.97
     Idaho
    0.95
     Alabama
    0.93
    Activations Density 0.223%

    No Known Activations