© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4321
    Prev
    Next
    INDEX
    Explanations

    constraints and limited resources

    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_13_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
     THROUGH
    0.90
     ujarnya
    0.89
     katanya
    0.88
     剤
    0.88
    ivided
    0.87
    oples
    0.86
     inversely
    0.85
    ९
    0.85
    ኘ
    0.85
    νον
    0.85
    POSITIVE LOGITS
     хотите
    2.24
     muốn
    1.95
     quieres
    1.91
     تريد
    1.88
     want
    1.83
    ต้องการ
    1.78
     ingin
    1.77
     souhaitez
    1.76
    你想
    1.72
     želite
    1.69
    Activations Density 1.080%

    No Known Activations